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

    Neuronpedia

    INDEX
    Explanations

    consent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extravag
    0.57
     unimagin
    0.54
     audacious
    0.53
     cashback
    0.52
     avantage
    0.52
    이사
    0.51
    ברי
    0.50
     azione
    0.50
    શ્
    0.50
     дисци
    0.50
    POSITIVE LOGITS
    Consent
    1.00
    consent
    0.84
     Consent
    0.82
     consent
    0.82
    ın
    0.64
     consentimiento
    0.64
    同意
    0.63
    関連
    0.60
    House
    0.58
     Einwill
    0.58
    Act Density 0.094%

    No Known Activations