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

    Neuronpedia

    INDEX
    Explanations

    being willing to act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    昙
    0.45
     நீர
    0.40
    Vé
    0.37
    Kabhi
    0.37
    勅
    0.36
     invál
    0.35
    ⿸
    0.34
     sAlarm
    0.34
     kz
    0.34
     LAKE
    0.34
    POSITIVE LOGITS
     willing
    3.56
     willingness
    3.44
    willing
    3.31
     Willing
    3.22
    愿意
    2.78
    願意
    2.59
     willingly
    2.02
     готовы
    1.79
     readiness
    1.71
     готов
    1.63
    Act Density 0.097%

    No Known Activations