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

    Neuronpedia

    INDEX
    Explanations

    rule, gate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.79
    abestanden
    -0.74
    पया
    -0.71
    tagHelperRunner
    -0.71
     itſelf
    -0.70
    YMMV
    -0.68
     rule
    -0.67
    Rujuakan
    -0.66
     незавершена
    -0.66
    )_/¯
    -0.66
    POSITIVE LOGITS
    Benzo
    0.42
     of
    0.41
     “
    0.41
     bin
    0.40
     cer
    0.40
    ijt
    0.39
     set
    0.39
    SetId
    0.39
     bem
    0.38
     SET
    0.38
    Act Density 0.138%

    No Known Activations