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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reign
    -0.07
     rainbow
    -0.07
    ψε
    -0.07
     Tight
    -0.07
    ）。↵↵
    -0.07
     Пост
    -0.07
    thesized
    -0.06
     tedious
    -0.06
     claiming
    -0.06
     resigned
    -0.06
    POSITIVE LOGITS
     molec
    0.07
    .win
    0.07
    ech
    0.07
    _utc
    0.06
    equal
    0.06
    ratings
    0.06
    욱
    0.06
    ék
    0.06
    oracle
    0.06
     finely
    0.06
    Act Density 0.015%

    No Known Activations