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

    Neuronpedia

    INDEX
    Explanations

    nonzero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moduleName
    -0.07
    추천
    -0.06
     Felix
    -0.06
    positor
    -0.06
    edere
    -0.06
     Yue
    -0.06
    $field
    -0.06
    dados
    -0.06
    zzo
    -0.06
     Submission
    -0.06
    POSITIVE LOGITS
     Cz
    0.07
     Blizzard
    0.07
    НЯ
    0.06
     """
↵
↵
    0.06
    艦
    0.06
     dword
    0.06
    paths
    0.06
    ysical
    0.06
     Parti
    0.06
    _org
    0.06
    Act Density 0.009%

    No Known Activations