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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wrongdoing
    -0.09
     lanjut
    -0.08
     замест
    -0.08
     непосредственно
    -0.08
    /Admin
    -0.08
     particulars
    -0.08
     mechanism
    -0.08
     pente
    -0.08
     اقدام
    -0.08
     вещества
    -0.08
    POSITIVE LOGITS
    典
    0.09
    Gray
    0.09
    经典
    0.08
     Gabri
    0.08
    Tokyo
    0.08
    typ
    0.08
     Grant
    0.08
    198
    0.08
    _GRAY
    0.08
    Grant
    0.08
    Act Density 0.005%

    No Known Activations