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

    Neuronpedia

    INDEX
    Explanations

    job requests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prisoner
    -0.07
     Wis
    -0.07
    🛑
    -0.07
     estoy
    -0.07
    Whenever
    -0.07
     »
    -0.07
    гер
    -0.07
    要在
    -0.07
    之所以
    -0.07
     kita
    -0.07
    POSITIVE LOGITS
    :'',↵
    0.08
    朴
    0.07
     СШ
    0.07
    _PLATFORM
    0.07
    𝙺
    0.07
    픕
    0.07
     компания
    0.07
     jp
    0.06
     firmly
    0.06
     lifting
    0.06
    Act Density 0.041%

    No Known Activations