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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :['
    -0.07
     said
    -0.07
     HttpMethod
    -0.06
    _pri
    -0.06
    .Horizontal
    -0.06
    .var
    -0.06
    ->
    -0.06
    _Edit
    -0.06
     polynomial
    -0.06
     hall
    -0.06
    POSITIVE LOGITS
     through
    0.07
     batter
    0.07
     allem
    0.07
    isArray
    0.07
    [right
    0.07
     THIRD
    0.07
     Batter
    0.07
    보고
    0.07
     squarely
    0.07
     Covered
    0.07
    Act Density 0.004%

    No Known Activations