Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    text related to data manipulation or processing commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens within or after curly braces

    np_acts-logits-general · gemini-2.0-flash

    substitute placeholders in strings and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.69
     onBackPressed
    -0.62
     اكتوبر
    -0.53
     conces
    -0.49
    ioutil
    -0.49
     ActionResult
    -0.49
     Socialista
    -0.48
     classifica
    -0.48
     Catto
    -0.48
     Shreve
    -0.47
    POSITIVE LOGITS
     replacements
    0.89
     replacement
    0.89
     replace
    0.87
     substituting
    0.83
     Substituting
    0.82
     substitution
    0.82
     substitutions
    0.81
     Replacement
    0.81
     replacing
    0.78
     substitute
    0.78
    Act Density 0.615%

    No Known Activations