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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ancellation
    -0.06
    ไม
    -0.06
    restricted
    -0.06
    ToList
    -0.06
    _related
    -0.06
    HSV
    -0.06
    uft
    -0.06
     Hugh
    -0.06
    린이
    -0.06
    upuncture
    -0.06
    POSITIVE LOGITS
    _FIX
    0.06
     중요
    0.06
    、二
    0.06
     σκ
    0.06
     splits
    0.06
     linea
    0.06
     ruined
    0.06
    cleanup
    0.06
    äs
    0.06
    ._
    0.05
    Act Density 0.098%

    No Known Activations