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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dua
    -0.07
    TRANS
    -0.07
    "S
    -0.07
    "C
    -0.07
     Initialize
    -0.07
     circumstance
    -0.07
     damages
    -0.07
    amaño
    -0.07
    iosis
    -0.06
    nąć
    -0.06
    POSITIVE LOGITS
    ibNameOrNil
    0.07
    膠
    0.07
    所以我们
    0.07
    ഏ
    0.07
    _library
    0.07
     Lans
    0.07
    考上
    0.07
    >f
    0.07
     ethn
    0.06
    最主要
    0.06
    Act Density 0.009%

    No Known Activations