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

    Neuronpedia

    INDEX
    Explanations

    memories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ألف
    -0.07
    𫠊
    -0.07
    (temp
    -0.07
    "]."
    -0.07
    рова
    -0.07
    _loader
    -0.06
    🄽
    -0.06
    _supported
    -0.06
    过度
    -0.06
    ).'
    -0.06
    POSITIVE LOGITS
    yc
    0.07
    ArrayType
    0.06
    女孩
    0.06
     kc
    0.06
    عص
    0.06
    ṇ
    0.06
    路
    0.06
    _PC
    0.06
    ucch
    0.06
     replay
    0.06
    Act Density 0.048%

    No Known Activations