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

    Neuronpedia

    INDEX
    Explanations

    phrases used within math argumentation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ãĤ·ãĥ¼
    -0.07
     Nghá»ĭ
    -0.07
    éĽĨä¸Ń
    -0.06
    ạm
    -0.06
    .Native
    -0.06
    plen
    -0.06
    _utilities
    -0.06
    _UNIQUE
    -0.06
    agnostic
    -0.06
    rup
    -0.05
    POSITIVE LOGITS
     first
    0.23
     second
    0.23
     third
    0.22
    first
    0.19
     fourth
    0.18
    第ä¸Ģ
    0.18
    second
    0.17
    第äºĮ
    0.16
    third
    0.16
    _first
    0.16
    Act Density 0.086%

    No Known Activations