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

    Neuronpedia

    INDEX
    Explanations

    performing a task

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     비밀
    -0.07
    USE
    -0.06
    _u
    -0.06
     Rescue
    -0.06
    _USE
    -0.06
     Purchase
    -0.06
    ゲ
    -0.06
     Rule
    -0.06
     sought
    -0.06
     favors
    -0.05
    POSITIVE LOGITS
    луг
    0.08
     自动生成
    0.07
     Mali
    0.07
    uron
    0.06
    isdigit
    0.06
    .mdl
    0.06
    _PA
    0.06
    'nın
    0.06
     dcc
    0.06
    대표
    0.06
    Act Density 0.188%

    No Known Activations