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

    Neuronpedia

    INDEX
    Explanations

    ->

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    삯
    -0.07
    .opens
    -0.07
     erklärt
    -0.07
     FAQs
    -0.07
    TemplateName
    -0.07
    傩
    -0.06
    텍
    -0.06
    뙇
    -0.06
     glGetUniformLocation
    -0.06
    _iso
    -0.06
    POSITIVE LOGITS
    .NonNull
    0.08
     Conor
    0.07
    BUY
    0.07
    ╨
    0.07
    blur
    0.07
    锒
    0.07
    ();++
    0.07
    我不想
    0.07
    (control
    0.07
    ระยะ
    0.06
    Act Density 0.009%

    No Known Activations