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

    Neuronpedia

    INDEX
    Explanations

    math typesetting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propaganda
    -0.07
    Web
    -0.07
    检查
    -0.07
    /');↵
    -0.06
    ose
    -0.06
     με
    -0.06
     tenía
    -0.06
     Lista
    -0.06
     button
    -0.06
    těl
    -0.06
    POSITIVE LOGITS
     کار
    0.07
    iş
    0.06
     اعتر
    0.06
    (tableName
    0.06
    ASY
    0.06
    ournaments
    0.06
     κορ
    0.06
     lãi
    0.06
    /git
    0.06
    .peek
    0.06
    Act Density 0.051%

    No Known Activations