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

    Neuronpedia

    INDEX
    Explanations

    IGN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _literal
    -0.07
     вперед
    -0.07
    itchen
    -0.07
    corev
    -0.06
     История
    -0.06
    wl
    -0.06
     면
    -0.06
     schwar
    -0.06
    okedex
    -0.06
     hỗn
    -0.06
    POSITIVE LOGITS
    program
    0.07
    (Game
    0.07
    ल
    0.07
    بود
    0.07
    Expense
    0.07
    [List
    0.06
    Ό
    0.06
    destruct
    0.06
     climb
    0.06
     Victory
    0.06
    Act Density 0.003%

    No Known Activations