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

    Neuronpedia

    INDEX
    Explanations

    em

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pandemic
    -0.06
    하신
    -0.06
     Auschwitz
    -0.06
     Donetsk
    -0.06
    .crypto
    -0.06
     Void
    -0.06
     slit
    -0.06
     Weapons
    -0.06
     breasts
    -0.06
     glaciers
    -0.06
    POSITIVE LOGITS
    \Exceptions
    0.07
     Gum
    0.07
    _${
    0.06
    股
    0.06
    ForgeryToken
    0.06
     Config
    0.06
    methodPointerType
    0.06
     فرض
    0.06
    nh
    0.06
    811
    0.06
    Act Density 0.003%

    No Known Activations