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

    Neuronpedia

    INDEX
    Explanations

    say "-"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    起草
    -0.07
    🅘
    -0.07
    欠缺
    -0.07
     obedient
    -0.07
    澳大
    -0.07
    >We
    -0.07
     béné
    -0.07
    ᵥ
    -0.07
    资源配置
    -0.07
     peri
    -0.07
    POSITIVE LOGITS
    첯
    0.07
     releasing
    0.07
    egan
    0.07
     switch
    0.06
     shim
    0.06
    عدد
    0.06
     Note
    0.06
     الجديد
    0.06
    鸡蛋
    0.06
     created
    0.06
    Act Density 0.000%

    No Known Activations