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

    Neuronpedia

    INDEX
    Explanations

    Foundation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _usec
    -0.08
     Naruto
    -0.07
     thrown
    -0.07
    'd
    -0.07
    ён
    -0.07
     surgical
    -0.07
     nuru
    -0.07
    接听
    -0.07
    تين
    -0.06
    윈
    -0.06
    POSITIVE LOGITS
    Alle
    0.08
    (rate
    0.08
    正面
    0.07
    ochen
    0.07
    _FT
    0.07
    早期
    0.07
     заказ
    0.07
    Rates
    0.07
    .standard
    0.07
    .feed
    0.07
    Act Density 0.001%

    No Known Activations