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

    Neuronpedia

    INDEX
    Explanations

    bootstrap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cliënten
    -0.09
    imizin
    -0.09
     Clement
    -0.08
     луч
    -0.08
    చ
    -0.08
     అభ
    -0.07
    argument
    -0.07
    SCH
    -0.07
     аналог
    -0.07
     অন
    -0.07
    POSITIVE LOGITS
    ിറ്റ്
    0.08
    ുവര
    0.08
     hundred
    0.07
    ാണ്
    0.07
     miatt
    0.07
     holiness
    0.07
    _patch
    0.07
    ishi
    0.07
     Hue
    0.07
     тен
    0.07
    Act Density 0.000%

    No Known Activations