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

    Neuronpedia

    INDEX
    Explanations

    1 or 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swallow
    -0.06
    醒
    -0.06
    ]:↵
    -0.06
     nou
    -0.06
    Autor
    -0.06
     prefs
    -0.06
     leaned
    -0.06
    >O
    -0.06
     услуг
    -0.06
     Wake
    -0.06
    POSITIVE LOGITS
     sham
    0.10
     Sham
    0.08
     gunfire
    0.07
    iedad
    0.07
    �
    0.07
    .destroy
    0.07
    :@"%@
    0.07
    -shared
    0.06
     crimes
    0.06
     남
    0.06
    Act Density 0.004%

    No Known Activations