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

    Neuronpedia

    INDEX
    Explanations

    ivariate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    afd
    -0.07
     condemnation
    -0.07
     اضافه
    -0.06
     ayar
    -0.06
     eşit
    -0.06
     mevcut
    -0.06
     restricting
    -0.06
    作为
    -0.06
     auditor
    -0.06
    ắng
    -0.06
    POSITIVE LOGITS
    lf
    0.07
    (stage
    0.07
     pyramid
    0.07
     Jamaica
    0.07
     inet
    0.06
    .emplace
    0.06
     laut
    0.06
    приєм
    0.06
     dar
    0.06
     (!!
    0.06
    Act Density 0.001%

    No Known Activations