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

    Neuronpedia

    INDEX
    Explanations

    levels and hierarchies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Libra
    -0.09
     linger
    -0.08
     libr
    -0.08
     подбор
    -0.08
     libra
    -0.08
     alten
    -0.07
    idus
    -0.07
     amino
    -0.07
    izer
    -0.07
     plated
    -0.07
    POSITIVE LOGITS
     स्तर
    0.16
    ระดับ
    0.14
     স্ত
    0.14
    级
    0.13
     ಮಟ್ಟ
    0.13
     estadual
    0.13
     સ્ત
    0.13
    .Level
    0.13
    _LEVEL
    0.13
    三级
    0.13
    Act Density 0.049%

    No Known Activations