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

    Neuronpedia

    INDEX
    Explanations

    cannot and will not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тивным
    0.83
     unwillingness
    0.76
    olischen
    0.73
    ாள்
    0.71
    rait
    0.70
    を与
    0.69
    requires
    0.68
    を与える
    0.68
    жет
    0.67
    atschapp
    0.67
    POSITIVE LOGITS
     have
    1.44
     want
    1.28
     are
    1.26
    have
    1.21
     cannot
    1.20
     believe
    1.19
     έχουν
    1.18
     têm
    1.18
     aren
    1.17
     tengo
    1.16
    Act Density 0.199%

    No Known Activations