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

    Neuronpedia

    INDEX
    Explanations

    code generation/file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KeyCode
    -0.06
     IDENT
    -0.06
    Communication
    -0.06
    图
    -0.06
     POT
    -0.06
     XVI
    -0.06
    _RED
    -0.06
    anity
    -0.06
    (types
    -0.06
     Its
    -0.06
    POSITIVE LOGITS
    417
    0.07
    鄉
    0.07
     milyon
    0.06
    ω
    0.06
    109
    0.06
     lifestyle
    0.06
    669
    0.06
    軍
    0.06
     Eg
    0.06
    出了
    0.06
    Act Density 0.000%

    No Known Activations