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

    Neuronpedia

    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     survived
    -0.07
    愿
    -0.07
    周年
    -0.06
     示例
    -0.06
    _Val
    -0.06
     return
    -0.06
     appears
    -0.06
     blob
    -0.06
     week
    -0.06
     cautioned
    -0.06
    POSITIVE LOGITS
    ..."↵
    0.06
     �
    0.06
     нов
    0.06
    แพร
    0.06
    ؟↵
    0.06
    getNum
    0.06
    tic
    0.06
    ую
    0.06
    RED
    0.06
    })"↵
    0.06
    Act Density 0.014%

    No Known Activations