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

    Neuronpedia

    INDEX
    Explanations

    someone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.66
     ketat
    -0.54
     alé
    -0.51
     cref
    -0.49
     automatiques
    -0.47
    abancı
    -0.47
    Slf
    -0.44
    一款
    -0.43
     صوتيه
    -0.43
     plomo
    -0.43
    POSITIVE LOGITS
     utafitiHapana
    0.71
    mtrl
    0.71
    WithIOException
    0.70
     Roskov
    0.69
    forKey
    0.66
     shewn
    0.65
     blest
    0.63
    Rüyada
    0.62
    ījum
    0.60
     Paglinawan
    0.59
    Act Density 0.011%

    No Known Activations