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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    沢
    -0.08
     Hockey
    -0.07
    wią
    -0.07
    PressEvent
    -0.07
    Assert
    -0.07
     mbedtls
    -0.07
     Baghdad
    -0.06
     kısmı
    -0.06
    무
    -0.06
     beni
    -0.06
    POSITIVE LOGITS
     behaviour
    0.06
     Chrom
    0.06
    _COR
    0.06
     experience
    0.06
    ουν
    0.06
    OURS
    0.06
    components
    0.06
     code
    0.06
    ournaments
    0.06
    ['__
    0.05
    Act Density 0.003%

    No Known Activations