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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    IDL
    -0.08
     lb
    -0.07
    CSR
    -0.07
     sortBy
    -0.07
     sost
    -0.07
    _as
    -0.07
     diferencia
    -0.07
    划算
    -0.07
    利器
    -0.07
    POSITIVE LOGITS
    (Be
    0.07
    烧
    0.07
    ичес
    0.07
    ้อม
    0.07
    .MON
    0.07
     scrub
    0.06
    -rock
    0.06
    ҷ
    0.06
    设备
    0.06
    -e
    0.06
    Act Density 0.046%

    No Known Activations