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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mezun
    -0.06
     liền
    -0.06
     wchar
    -0.06
    Decorator
    -0.06
    (domain
    -0.06
    =target
    -0.06
    _pa
    -0.06
     можете
    -0.06
     FindObjectOfType
    -0.06
     maken
    -0.06
    POSITIVE LOGITS
     College
    0.07
     "|
    0.07
    iming
    0.07
    ton
    0.06
    DisplayName
    0.06
     Nigel
    0.06
    askets
    0.06
    岛
    0.06
     Justin
    0.06
    %";↵
    0.06
    Act Density 0.161%

    No Known Activations