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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CPI
    -0.07
     initi
    -0.07
    Dat
    -0.06
     hope
    -0.06
     meilleur
    -0.06
     Вік
    -0.06
     synonym
    -0.06
     nir
    -0.06
     문화
    -0.06
     antibiotics
    -0.06
    POSITIVE LOGITS
     dbus
    0.06
     Celtics
    0.06
    ished
    0.06
    hcp
    0.06
    -making
    0.06
    _LOGGER
    0.06
    HWND
    0.06
    .sharedInstance
    0.05
     Silva
    0.05
    softmax
    0.05
    Act Density 0.000%

    No Known Activations