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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    haps
    -0.07
     路
    -0.07
     SUV
    -0.06
    bai
    -0.06
    tb
    -0.06
    tk
    -0.06
    Venta
    -0.06
    购
    -0.06
    หนด
    -0.06
    neh
    -0.06
    POSITIVE LOGITS
    .Content
    0.07
    .getLocal
    0.06
     productions
    0.06
    frames
    0.06
    .onError
    0.06
     bezpeč
    0.06
    >Action
    0.06
     auditing
    0.06
    _act
    0.06
     لك
    0.06
    Act Density 0.002%

    No Known Activations