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

    Neuronpedia

    INDEX
    Explanations

    time (AM and PM)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =top
    -0.07
    /plain
    -0.07
     getParent
    -0.07
    .assertIsInstance
    -0.07
     bef
    -0.07
    (pdev
    -0.07
    _initialized
    -0.07
     pooling
    -0.07
     ambiguity
    -0.07
    (cn
    -0.07
    POSITIVE LOGITS
    _dem
    0.07
     Marxist
    0.07
     האמר
    0.07
    ทรา
    0.07
    contracts
    0.07
    _EXTRA
    0.07
    _characters
    0.06
    史料
    0.06
    INTER
    0.06
     DECL
    0.06
    Act Density 0.003%

    No Known Activations