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

    Neuronpedia

    INDEX
    Explanations

    umbrella

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    號
    -0.09
    (".
    -0.07
    杧
    -0.07
    않
    -0.07
    歳
    -0.07
    인
    -0.07
    호
    -0.07
    .getData
    -0.07
     nighttime
    -0.06
    .Audio
    -0.06
    POSITIVE LOGITS
     Chamber
    0.08
     unearth
    0.08
    �
    0.07
    Bool
    0.07
    𬭚
    0.07
    osaur
    0.07
    紧缺
    0.07
     ponder
    0.07
     compliant
    0.07
     заб
    0.07
    Act Density 0.003%

    No Known Activations