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

    Neuronpedia

    INDEX
    Explanations

    blues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    吃饱
    -0.07
     dew
    -0.07
     processData
    -0.06
    Ử
    -0.06
    nect
    -0.06
    ሾ
    -0.06
    🖖
    -0.06
    IAN
    -0.06
    Much
    -0.06
    债务
    -0.06
    POSITIVE LOGITS
    城管
    0.08
    .hh
    0.07
     advertiser
    0.07
    ornment
    0.07
     founded
    0.07
     Comment
    0.07
    -comm
    0.07
     Platt
    0.07
    会导致
    0.07
    validation
    0.07
    Act Density 0.003%

    No Known Activations