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

    Neuronpedia

    INDEX
    Explanations

    conditions and exceptions related to regulations or protocols

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

    "Unless," "except," or "in compliance" conditional statements

    np_acts-logits-general · gemini-2.0-flash

    exceptions and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.67
     ſeveral
    -0.62
    脚注の使い方
    -0.62
     lefs
    -0.61
     AssemblyCulture
    -0.60
     différente
    -0.59
     leſs
    -0.59
    TagMode
    -0.58
     aught
    -0.58
     feveral
    -0.58
    POSITIVE LOGITS
     extremely
    0.85
     absolutely
    0.81
     very
    0.74
     explicitly
    0.72
     carefully
    0.72
    rungsseite
    0.71
     exceptionally
    0.70
     extreme
    0.69
    absolutely
    0.69
     specifically
    0.69
    Act Density 0.425%

    No Known Activations