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

    Neuronpedia

    INDEX
    Explanations

    -time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pressed
    -0.08
     filled
    -0.07
    젴
    -0.07
    (sb
    -0.07
     cabeça
    -0.07
     cabinets
    -0.07
    Detail
    -0.07
     favourites
    -0.07
    filled
    -0.07
    ビー
    -0.06
    POSITIVE LOGITS
    分散
    0.08
    되고
    0.07
     создан
    0.07
    犷
    0.07
     KR
    0.07
     ------
    0.07
     Conce
    0.06
     Parl
    0.06
     السل
    0.06
    пан
    0.06
    Act Density 0.022%

    No Known Activations