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

    Neuronpedia

    INDEX
    Explanations

    information and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    此之外
    1.18
    を取得
    0.88
     Благодаря
    0.84
    ích
    0.84
    küm
    0.84
    k
    0.84
    Mình
    0.84
    तुरंग
    0.83
    ￠
    0.81
     TestBed
    0.80
    POSITIVE LOGITS
    و
    1.13
     πως
    1.01
     resultContent
    0.88
     conta
    0.88
     acondicionado
    0.84
    ดิ
    0.80
     informazioni
    0.77
     renseign
    0.77
     contacto
    0.77
     compres
    0.76
    Act Density 0.313%

    No Known Activations