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

    Neuronpedia

    INDEX
    Explanations

    split

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    animation
    -0.07
    says
    -0.07
    Assert
    -0.07
    optimizer
    -0.06
     movie
    -0.06
    �
    -0.06
    [J
    -0.06
    _logger
    -0.06
     dismant
    -0.06
    ोक
    -0.06
    POSITIVE LOGITS
    _BROWSER
    0.07
    isses
    0.06
     الرح
    0.06
     Kro
    0.06
     Пів
    0.06
     Lum
    0.06
    sensor
    0.06
    ["_
    0.06
     Bowman
    0.06
     indeb
    0.06
    Act Density 0.004%

    No Known Activations