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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Комп
    -0.07
     очи
    -0.06
    레벨
    -0.06
    .Tests
    -0.06
     careful
    -0.06
     powerful
    -0.06
    responses
    -0.06
    methodPointerType
    -0.06
     leave
    -0.05
     sagen
    -0.05
    POSITIVE LOGITS
    WindowSize
    0.07
     prefs
    0.07
     firearms
    0.07
     tỷ
    0.07
    cakes
    0.06
     İŞ
    0.06
    adiens
    0.06
    solete
    0.06
     PRIV
    0.06
     FLAGS
    0.06
    Act Density 0.024%

    No Known Activations