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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    صندوق
    -0.07
    ♩
    -0.07
    宝马
    -0.07
     teg
    -0.07
     тор
    -0.06
     unseren
    -0.06
    💕
    -0.06
    容量
    -0.06
    xcc
    -0.06
     dateFormatter
    -0.06
    POSITIVE LOGITS
    Ignore
    0.08
    .frames
    0.07
     Hait
    0.07
    attles
    0.07
    ？↵
    0.06
    ?t
    0.06
     Efficient
    0.06
    -CS
    0.06
    .must
    0.06
    Agent
    0.06
    Act Density 0.018%

    No Known Activations