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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    burger
    -0.07
    FIELDS
    -0.07
    hex
    -0.06
     ремонт
    -0.06
    enguin
    -0.06
    _spin
    -0.06
     Ergebn
    -0.06
     flutter
    -0.06
    �
    -0.06
     Flower
    -0.06
    POSITIVE LOGITS
     UNITED
    0.07
    ーバ
    0.07
    [in
    0.06
     организма
    0.06
     millones
    0.06
    ヤ
    0.06
     USD
    0.06
    .y
    0.06
     گزارش
    0.06
    त
    0.06
    Act Density 0.044%

    No Known Activations