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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    project
    -0.06
    capital
    -0.06
    .Low
    -0.06
     Müdür
    -0.06
     یعنی
    -0.06
     genocide
    -0.06
    endar
    -0.06
    langs
    -0.06
     kok
    -0.06
     IsNot
    -0.06
    POSITIVE LOGITS
     Ah
    0.07
     busty
    0.06
     Sync
    0.06
    ़ी
    0.06
     motel
    0.06
    borah
    0.06
    .Sys
    0.06
    istributed
    0.06
     vé
    0.06
    cret
    0.06
    Act Density 0.009%

    No Known Activations