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

    Neuronpedia

    INDEX
    Explanations

    attention spans and technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trium
    -0.08
    :absolute
    -0.08
     היית
    -0.08
    uebla
    -0.08
     תוכלו
    -0.08
     Maison
    -0.08
    .Server
    -0.07
    fangen
    -0.07
    ర్వ
    -0.07
     Hou
    -0.07
    POSITIVE LOGITS
    习
    0.09
    習
    0.09
     conséquence
    0.08
     strtok
    0.08
     ког
    0.08
     acostumbr
    0.08
     shorter
    0.08
     sober
    0.08
     endurance
    0.08
    跨度
    0.08
    Act Density 0.008%

    No Known Activations