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

    Neuronpedia

    INDEX
    Explanations

    Unstructured/Mixed Data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rosso
    -0.07
     spoiled
    -0.06
     rescue
    -0.06
     Zak
    -0.06
     Serum
    -0.06
    credited
    -0.06
    sters
    -0.06
    Pear
    -0.06
     synonym
    -0.06
     stats
    -0.06
    POSITIVE LOGITS
    旅行
    0.07
    ";//
    0.07
    _passwd
    0.07
    \GeneratedValue
    0.07
     "/");↵
    0.06
    }")
    0.06
     cerr
    0.06
     titleLabel
    0.06
    cran
    0.06
    '})
    0.06
    Act Density 0.025%

    No Known Activations