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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rounded
    -0.09
    Rounded
    -0.08
    <|reserved_200016|>
    -0.08
    -round
    -0.08
    -op
    -0.08
     ಮತ್ತು
    -0.08
     rounding
    -0.08
    _op
    -0.07
    Chunk
    -0.07
    Op
    -0.07
    POSITIVE LOGITS
    idy
    0.09
    	sizeof
    0.09
     treats
    0.09
     suprem
    0.08
     Berkeley
    0.08
     선언
    0.08
     Revista
    0.08
     embeddings
    0.08
     tratar
    0.08
    anoj
    0.08
    Act Density 0.037%

    No Known Activations