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

    Neuronpedia

    INDEX
    Explanations

    consent and willingness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     நுண்ண
    0.87
    debug
    0.82
    Debug
    0.77
     debug
    0.76
     Pierce
    0.76
     debugging
    0.75
     debugger
    0.74
    nmid
    0.73
     closer
    0.73
    debugging
    0.71
    POSITIVE LOGITS
     voluntary
    1.75
     consent
    1.65
     Voluntary
    1.60
     volunt
    1.59
    Consent
    1.59
     Consent
    1.59
     consentement
    1.53
     voluntarily
    1.51
     willingly
    1.48
     consentimiento
    1.47
    Act Density 0.537%

    No Known Activations