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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isco
    -0.07
     Daniel
    -0.07
     thiệu
    -0.06
    ideshow
    -0.06
     tudo
    -0.06
     Hugh
    -0.06
    _until
    -0.06
     svc
    -0.06
    Ben
    -0.06
     FL
    -0.06
    POSITIVE LOGITS
    战火
    0.08
     Applied
    0.07
    loss
    0.07
    ämp
    0.07
    onnen
    0.07
    -backed
    0.07
     shaped
    0.07
     มกร
    0.07
    مراقب
    0.07
    Gamma
    0.06
    Act Density 0.011%

    No Known Activations