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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ders
    -0.07
    梦
    -0.07
    Proveedor
    -0.07
     ве
    -0.07
     워
    -0.06
     کمتر
    -0.06
     Tanner
    -0.06
     сч
    -0.06
     =================================================================================
    -0.06
    ังส
    -0.06
    POSITIVE LOGITS
    .String
    0.07
    )[
    0.07
    utenant
    0.07
    ??
    0.07
     selection
    0.06
    initial
    0.06
    ि
    0.06
    assume
    0.06
    mock
    0.06
     ac
    0.06
    Act Density 0.004%

    No Known Activations