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

    Neuronpedia

    INDEX
    Explanations

    addSubview

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANC
    -0.08
    栋
    -0.07
    بدو
    -0.07
     😀
    -0.07
    を開
    -0.07
    undra
    -0.07
    ando
    -0.07
    indi
    -0.07
    inidad
    -0.07
     unh
    -0.07
    POSITIVE LOGITS
    .azure
    0.07
    手中
    0.07
     Straw
    0.07
    UserCode
    0.07
    [args
    0.07
    .warn
    0.06
    (weight
    0.06
     item
    0.06
    $",
    0.06
     affair
    0.06
    Act Density 0.001%

    No Known Activations