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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ton
    -0.07
    GB
    -0.06
     Lo
    -0.06
    nets
    -0.06
    azes
    -0.06
     zar
    -0.06
     consid
    -0.06
     Italians
    -0.06
     Norse
    -0.06
     Greene
    -0.06
    POSITIVE LOGITS
    (strict
    0.07
    .asInstanceOf
    0.07
    stk
    0.06
    찰
    0.06
     wearable
    0.06
    ceipt
    0.06
    LECT
    0.06
     bằng
    0.06
    ротив
    0.06
    '},↵
    0.06
    Act Density 0.030%

    No Known Activations