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

    Neuronpedia

    INDEX
    Explanations

    semicolon or parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wave
    -0.07
    Ni
    -0.06
    AGEMENT
    -0.06
    RITE
    -0.06
    目标
    -0.06
    Walker
    -0.06
    ارد
    -0.06
    IGATION
    -0.06
    Aqu
    -0.06
     member
    -0.06
    POSITIVE LOGITS
    .aspx
    0.07
     خیلی
    0.07
     khám
    0.07
    [href
    0.06
    古屋
    0.06
    けど
    0.06
    -bal
    0.06
     belang
    0.06
     peso
    0.06
    _rw
    0.06
    Act Density 0.017%

    No Known Activations