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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OA
    -0.08
     loyalty
    -0.07
     Porto
    -0.06
    European
    -0.06
    FileSize
    -0.06
    Europe
    -0.06
    _modified
    -0.06
    اسات
    -0.06
     类
    -0.06
    Ability
    -0.06
    POSITIVE LOGITS
     batching
    0.07
     translates
    0.07
    WhiteSpace
    0.06
    mmo
    0.06
     facil
    0.06
     cere
    0.06
     gratuite
    0.06
     DISTINCT
    0.06
    ????
    0.06
     Blake
    0.06
    Act Density 0.009%

    No Known Activations