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

    Neuronpedia

    INDEX
    Explanations

    qualities and freedoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grosso
    0.41
     matte
    0.40
     isom
    0.38
     alike
    0.38
     panier
    0.37
     nein
    0.37
     equilibr
    0.36
     dominions
    0.36
    Nope
    0.36
     inlay
    0.36
    POSITIVE LOGITS
    寻找
    0.42
    тят
    0.40
    থা
    0.40
     Commitment
    0.39
    信息的
    0.38
    避免
    0.37
    aspetto
    0.37
     выбирать
    0.37
    នៃការ
    0.37
     Environmental
    0.37
    Act Density 0.238%

    No Known Activations