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

    Neuronpedia

    INDEX
    Explanations

    se

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arial
    -0.06
    Arn
    -0.06
    _BL
    -0.06
    Handled
    -0.06
     schle
    -0.06
    词
    -0.06
    istributions
    -0.06
    >In
    -0.06
    복
    -0.06
     води
    -0.06
    POSITIVE LOGITS
    ožná
    0.06
    )section
    0.06
     protection
    0.06
    러스
    0.06
     saturated
    0.06
     notifier
    0.06
     فضای
    0.06
    вет
    0.06
    letes
    0.06
    :ss
    0.06
    Act Density 0.004%

    No Known Activations