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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    shouldBe
    -0.07
     lagi
    -0.07
    unknown
    -0.07
    {n
    -0.07
     DSM
    -0.07
    (NUM
    -0.06
    .М
    -0.06
     relay
    -0.06
    -outs
    -0.06
     mbox
    -0.06
    POSITIVE LOGITS
    orean
    0.06
    amilia
    0.06
     emailing
    0.06
    NSNumber
    0.06
     rápido
    0.06
    限
    0.06
    .toast
    0.06
    _charset
    0.06
     Categoria
    0.06
     Attorney
    0.06
    Act Density 0.157%

    No Known Activations