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

    Neuronpedia

    INDEX
    Explanations

    positive descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARSE
    -0.07
    Linked
    -0.07
     replay
    -0.07
     briefly
    -0.06
     Fi
    -0.06
    는다
    -0.06
     milliseconds
    -0.06
    ERVED
    -0.06
     comenz
    -0.06
    _motion
    -0.06
    POSITIVE LOGITS
     Presents
    0.07
     tờ
    0.07
    []={
    0.07
    _AspNet
    0.07
    대로
    0.06
    .Verify
    0.06
    领导
    0.06
    (BigInteger
    0.06
     respondent
    0.06
     Culture
    0.06
    Act Density 0.026%

    No Known Activations