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

    Neuronpedia

    INDEX
    Explanations

    tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，没有
    -0.07
    buckets
    -0.06
    (Local
    -0.06
     withdrawing
    -0.06
    ,options
    -0.06
    へと
    -0.06
    ?");↵
    -0.06
     blueprint
    -0.06
     Hum
    -0.06
    立刻
    -0.06
    POSITIVE LOGITS
    ábado
    0.07
    sehen
    0.07
    圭圭
    0.06
    ุด
    0.06
    اعت
    0.06
    ानन
    0.06
    ......
    0.06
     wage
    0.06
     glare
    0.06
    alizace
    0.06
    Act Density 0.012%

    No Known Activations