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

    Neuronpedia

    INDEX
    Explanations

    Code/Software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oland
    -0.07
     subclass
    -0.07
    _cp
    -0.07
    _DOT
    -0.07
    ']],↵
    -0.07
    ("");↵
    -0.07
    emann
    -0.07
     نسب
    -0.06
    imate
    -0.06
     FileType
    -0.06
    POSITIVE LOGITS
     ela
    0.07
     entonces
    0.06
    ẵn
    0.06
    лося
    0.06
     rethink
    0.06
    .#
    0.05
    (er
    0.05
    ‌دان
    0.05
     architekt
    0.05
     unos
    0.05
    Act Density 0.104%

    No Known Activations