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

    Neuronpedia

    INDEX
    Explanations

    prompt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الشي
    -0.08
    ocy
    -0.07
    _IO
    -0.07
    570
    -0.07
    /loading
    -0.07
     spas
    -0.07
    hair
    -0.06
     ústav
    -0.06
    ixin
    -0.06
     tree
    -0.06
    POSITIVE LOGITS
    搭
    0.06
     используют
    0.06
     disgrace
    0.06
    Parsing
    0.06
     가정
    0.06
    immune
    0.06
     पढ
    0.06
     kork
    0.06
    Highlighted
    0.06
     Valor
    0.06
    Act Density 0.011%

    No Known Activations