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

    Neuronpedia

    INDEX
    Explanations

    references to rules and regulations

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

    rules and procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    かつて
    -0.42
    acaktır
    -0.40
    maktadır
    -0.38
     localized
    -0.37
     Standort
    -0.37
    THESIS
    -0.36
     Exploring
    -0.36
     Localization
    -0.36
     Packard
    -0.35
     çe
    -0.35
    POSITIVE LOGITS
     rule
    1.85
     rules
    1.78
    Rule
    1.73
     Rule
    1.72
     Rules
    1.70
    Rules
    1.67
     RULE
    1.66
     RULES
    1.61
    rules
    1.59
    rule
    1.56
    Act Density 0.068%

    No Known Activations