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

    Neuronpedia

    INDEX
    Explanations

    medical conditions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    变革
    0.50
    观看
    0.44
     umożliw
    0.44
    帮
    0.42
    ę
    0.42
    ".$
    0.41
    ună
    0.40
    룺
    0.40
     ศ
    0.39
     поддержка
    0.39
    POSITIVE LOGITS
     steeply
    0.48
    ziehen
    0.42
    zev
    0.42
     Bruder
    0.41
     obliquely
    0.41
    ಾಗಿತ್ತು
    0.41
     disturbed
    0.41
     invaded
    0.41
     cooled
    0.40
     hijacked
    0.40
    Act Density 0.007%

    No Known Activations