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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dělen
    -0.07
    izon
    -0.07
    _();↵
    -0.07
    $new
    -0.07
     Calcul
    -0.07
    料
    -0.07
    [y
    -0.06
    ugu
    -0.06
    plers
    -0.06
    Finite
    -0.06
    POSITIVE LOGITS
     informing
    0.06
    TickCount
    0.06
    _gradients
    0.06
     mandate
    0.06
     destroying
    0.06
     favor
    0.06
     addObject
    0.06
     =================================
    0.06
     advocating
    0.06
     bieten
    0.06
    Act Density 0.021%

    No Known Activations