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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    finity
    -0.08
    _SWAP
    -0.07
    람
    -0.07
    'all
    -0.06
    品
    -0.06
    _pitch
    -0.06
     Ward
    -0.06
    Rail
    -0.06
    _af
    -0.06
     ста
    -0.06
    POSITIVE LOGITS
     hospodář
    0.07
    ..↵
    0.07
     Hess
    0.07
     conhec
    0.07
     내
    0.06
     wider
    0.06
     Cards
    0.06
     Mitt
    0.06
     breadth
    0.06
    稍
    0.06
    Act Density 0.021%

    No Known Activations