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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    κα
    -0.08
    _bag
    -0.07
     khỏe
    -0.06
    [])
↵
    -0.06
    ゞ
    -0.06
    ラン
    -0.06
     eoq
    -0.06
    ictionary
    -0.05
    cych
    -0.05
    doi
    -0.05
    POSITIVE LOGITS
    ]",
    0.07
     powerless
    0.06
    recover
    0.06
     Dynamic
    0.06
    _USAGE
    0.06
     Colts
    0.06
     Martha
    0.06
     genders
    0.06
     PropertyChanged
    0.06
    _unused
    0.06
    Act Density 0.006%

    No Known Activations