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

    Neuronpedia

    INDEX
    Explanations

    commas/periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    سم
    -0.09
     funciones
    -0.07
    ⵏ
    -0.07
     ocas
    -0.07
    .elem
    -0.07
    了过来
    -0.07
     cherished
    -0.07
    _ZONE
    -0.07
    .Utils
    -0.07
    עול
    -0.06
    POSITIVE LOGITS
    两个月
    0.08
    Sequential
    0.08
    порт
    0.08
    拖欠
    0.07
     interracial
    0.07
    相对于
    0.07
     bw
    0.07
    ("--
    0.07
     divorced
    0.06
     Interracial
    0.06
    Act Density 0.054%

    No Known Activations