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

    Neuronpedia

    INDEX
    Explanations

    corpus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -chat
    -0.06
    Classification
    -0.06
    _hold
    -0.06
     introdu
    -0.06
    _call
    -0.06
    ade
    -0.06
    969
    -0.06
    VN
    -0.06
    ních
    -0.06
    _fe
    -0.06
    POSITIVE LOGITS
     corpus
    0.12
     Corpus
    0.11
     Iris
    0.07
     corpor
    0.07
     çalışma
    0.07
     Umb
    0.07
     accountId
    0.06
     Å
    0.06
    ！",
    0.06
     thấy
    0.06
    Act Density 0.002%

    No Known Activations