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

    Neuronpedia

    INDEX
    Explanations

    alike

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ThanOr
    -0.07
    Steven
    -0.07
     เบ
    -0.06
    strpos
    -0.06
    //}↵↵
    -0.06
     RCS
    -0.06
    ----------</
    -0.06
    ulla
    -0.06
     converters
    -0.06
    .isdigit
    -0.06
    POSITIVE LOGITS
     same
    0.07
     alike
    0.06
    _duplicate
    0.06
    itous
    0.06
    lasses
    0.06
    .lambda
    0.06
    培训
    0.06
    Ont
    0.06
    爱
    0.06
    λεκ
    0.06
    Act Density 0.002%

    No Known Activations