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

    Neuronpedia

    INDEX
    Explanations

    means

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NEG
    -0.08
    <float
    -0.06
     查
    -0.06
    Plot
    -0.06
     evaluating
    -0.06
    xl
    -0.06
    .concat
    -0.06
     İz
    -0.06
     exercised
    -0.06
     amid
    -0.06
    POSITIVE LOGITS
    074
    0.06
    psilon
    0.06
     mans
    0.06
    smarty
    0.06
     tph
    0.06
    ольку
    0.06
    CustomerId
    0.06
     U
    0.06
    058
    0.06
    Mayor
    0.06
    Act Density 0.029%

    No Known Activations