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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Steel
    -0.07
     Signature
    -0.07
    .RESET
    -0.07
    Old
    -0.06
     Needless
    -0.06
    %
    -0.06
     Stout
    -0.06
     Studi
    -0.06
     stuff
    -0.06
    adelphia
    -0.06
    POSITIVE LOGITS
     adj
    0.06
    户
    0.06
     bu
    0.06
    .transactions
    0.06
    Mutable
    0.06
    扬
    0.06
    廷
    0.06
    .adj
    0.06
    _sess
    0.06
    acion
    0.06
    Act Density 0.129%

    No Known Activations