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

    Neuronpedia

    INDEX
    Explanations

    considerations or intentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    取り組み
    0.68
    我們會
    0.63
     बाती
    0.61
     보
    0.61
    是我
    0.61
     phenomenon
    0.60
    Continued
    0.59
     продов
    0.59
    Quer
    0.59
    ขอ
    0.59
    POSITIVE LOGITS
     mind
    1.28
    mind
    1.12
     दिमाग
    1.03
     MIND
    0.94
     minds
    0.94
     Mind
    0.93
    Mind
    0.88
     ready
    0.88
     pikiran
    0.88
     ذہن
    0.86
    Act Density 0.244%

    No Known Activations