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

    Neuronpedia

    INDEX
    Explanations

    field

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    654
    -0.07
     právě
    -0.07
    Лю
    -0.07
    Framebuffer
    -0.06
    ительное
    -0.06
     DefaultValue
    -0.06
    就
    -0.06
    probability
    -0.06
    704
    -0.06
     phút
    -0.06
    POSITIVE LOGITS
     коміс
    0.07
    ční
    0.06
     ^{}
    0.06
    fte
    0.06
    방
    0.06
     ؛
    0.06
     ("-
    0.06
    vinfos
    0.06
    issional
    0.06
     agre
    0.06
    Act Density 0.028%

    No Known Activations