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

    Neuronpedia

    INDEX
    Explanations

    Evaluation/Judgement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fixed
    -0.07
    父亲
    -0.06
    Arrays
    -0.06
     resulted
    -0.06
     Creator
    -0.06
    +-+-
    -0.06
    .adjust
    -0.06
    灯
    -0.06
     destabil
    -0.06
    ')))
    -0.06
    POSITIVE LOGITS
     Zo
    0.07
     Đại
    0.07
     бактер
    0.07
     yö
    0.07
    Io
    0.07
     mädchen
    0.07
     Mär
    0.07
     ayrıntılı
    0.06
    edii
    0.06
    _NATIVE
    0.06
    Act Density 0.523%

    No Known Activations