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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \modules
    -0.08
    ług
    -0.07
     Fan
    -0.07
     aktuellen
    -0.06
    нов
    -0.06
     klas
    -0.06
    :update
    -0.06
    (runtime
    -0.06
     assumptions
    -0.06
    _voltage
    -0.06
    POSITIVE LOGITS
    Segoe
    0.07
    ++)
    0.06
    离
    0.06
    679
    0.06
     newArr
    0.06
     ATK
    0.06
     Sanctuary
    0.06
    xA
    0.06
     scripted
    0.06
    �
    0.06
    Act Density 0.013%

    No Known Activations