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

    Neuronpedia

    INDEX
    Explanations

    a, an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    опас
    -0.07
     fodder
    -0.07
     Lud
    -0.07
     Indians
    -0.07
     Vanilla
    -0.06
    oje
    -0.06
     statistically
    -0.06
     Policy
    -0.06
     renowned
    -0.06
    .Source
    -0.06
    POSITIVE LOGITS
    となり
    0.07
    =a
    0.06
    。」
    0.06
     لت
    0.06
    。</
    0.06
    "]),
    0.06
    .news
    0.06
     σαν
    0.06
    "><
    0.06
    らない
    0.06
    Act Density 0.055%

    No Known Activations