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

    Neuronpedia

    INDEX
    Explanations

    counts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /she
    -0.07
    .Zoom
    -0.07
     Tibet
    -0.06
     Kore
    -0.06
     internet
    -0.06
     Border
    -0.06
    CY
    -0.06
    DSL
    -0.06
    Pipeline
    -0.06
     musí
    -0.06
    POSITIVE LOGITS
    unakan
    0.07
     Ptr
    0.07
     toReturn
    0.07
    <Scalars
    0.07
    хови
    0.06
    CppClass
    0.06
    ğını
    0.06
    ρευ
    0.06
     category
    0.06
    ęki
    0.06
    Act Density 0.002%

    No Known Activations