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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rol
    -0.07
     humanity
    -0.07
    ↘
    -0.07
    联赛
    -0.07
     القدم
    -0.07
    "To
    -0.07
    scala
    -0.07
    Eq
    -0.07
    iggs
    -0.07
     Veter
    -0.07
    POSITIVE LOGITS
     пара
    0.08
    爆出
    0.07
    퓔
    0.07
     paar
    0.07
    接过
    0.06
     היהודי
    0.06
     Magnus
    0.06
    เทคโน
    0.06
     órg
    0.06
    wash
    0.06
    Act Density 0.027%

    No Known Activations