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

    Neuronpedia

    INDEX
    Explanations

    large

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    slot
    -0.06
    عي
    -0.06
    „ظ
    -0.06
    وج
    -0.06
    lename
    -0.06
     امر
    -0.06
    axed
    -0.06
    /Getty
    -0.06
    sky
    -0.06
     Marriage
    -0.06
    POSITIVE LOGITS
    ;-
    0.07
    ubbles
    0.07
     Individual
    0.06
    0.06
    (Expression
    0.06
    innamon
    0.06
    uenta
    0.06
     mainly
    0.06
     ClassName
    0.06
     adding
    0.06
    Act Density 0.021%

    No Known Activations