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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     posix
    -0.06
     Alexand
    -0.06
    -स
    -0.06
     murders
    -0.06
    _removed
    -0.06
     Coinbase
    -0.06
    國家
    -0.06
    ugador
    -0.05
     sağlık
    -0.05
    /filter
    -0.05
    POSITIVE LOGITS
    ificantly
    0.07
     getContent
    0.07
    _ring
    0.07
    icult
    0.07
    _block
    0.07
     Thousand
    0.06
     noun
    0.06
    Input
    0.06
    cretion
    0.06
     solidity
    0.06
    Act Density 0.002%

    No Known Activations