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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mutants
    -0.07
    .download
    -0.07
    -forward
    -0.06
    .List
    -0.06
     Ingen
    -0.06
    .City
    -0.06
    .Doc
    -0.06
     Dund
    -0.06
    .cert
    -0.06
    million
    -0.06
    POSITIVE LOGITS
     assistir
    0.06
     communicated
    0.06
     FACT
    0.06
     submodule
    0.06
     joked
    0.06
     조금
    0.06
     skl
    0.06
    feat
    0.06
    urent
    0.06
     هنگام
    0.06
    Act Density 0.256%

    No Known Activations