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

    Neuronpedia

    INDEX
    Explanations

    operator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pins
    -0.07
    出发
    -0.07
    [char
    -0.07
    ��
    -0.07
    wa
    -0.07
     Jones
    -0.07
     Pink
    -0.06
    ورد
    -0.06
    一朵
    -0.06
    喪
    -0.06
    POSITIVE LOGITS
    ⊶
    0.07
    <dyn
    0.07
    ӣ
    0.07
    쵝
    0.07
    <S
    0.07
    0.07
     MIS
    0.07
    سائر
    0.06
    🎼
    0.06
    toJson
    0.06
    Act Density 0.018%

    No Known Activations