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

    Neuronpedia

    INDEX
    Explanations

    scientific experiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    原著
    -0.07
    �
    -0.07
    眠
    -0.06
    仅代表
    -0.06
    different
    -0.06
    SupportedException
    -0.06
     ecosystem
    -0.06
    $search
    -0.06
     Eur
    -0.06
    휏
    -0.06
    POSITIVE LOGITS
     Tempo
    0.07
    ivicrm
    0.07
    _SL
    0.07
    .tencent
    0.07
    _avatar
    0.06
     referral
    0.06
    .global
    0.06
    .Label
    0.06
    .Bool
    0.06
    ube
    0.06
    Act Density 0.042%

    No Known Activations