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

    Neuronpedia

    INDEX
    Explanations

    negations related to personal preferences or tendencies

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

    Negation or uncertainty

    np_acts-logits-general · gemini-2.0-flash

    dislike or no preference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tableFuture
    -0.66
     AssemblyCulture
    -0.56
    errHandler
    -0.54
     @"/
    -0.54
    клопе
    -0.54
    popo
    -0.53
    FieldError
    -0.51
    enschappelijke
    -0.50
    MENAFN
    -0.49
    ApiModelProperty
    -0.48
    POSITIVE LOGITS
     preferring
    0.74
     preferences
    0.73
     prefers
    0.71
     предпочита
    0.70
     предпоч
    0.65
     préférence
    0.65
     preference
    0.62
    preference
    0.60
     gusta
    0.60
     Preference
    0.59
    Act Density 0.313%

    No Known Activations