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

    Neuronpedia

    INDEX
    Explanations

    numerical ratios or counts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     composer
    -0.08
     collectibles
    -0.08
     gist
    -0.08
     नई
    -0.07
     Composer
    -0.07
    чера
    -0.07
     höchste
    -0.07
     Maks
    -0.07
    高度
    -0.07
     spanning
    -0.07
    POSITIVE LOGITS
    _cipher
    0.09
    _noise
    0.08
     duplex
    0.08
    _S
    0.08
    Overlap
    0.08
    Swimming
    0.08
    _overlap
    0.08
    Noise
    0.08
    _neg
    0.08
    cipher
    0.08
    Act Density 0.030%

    No Known Activations