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

    Neuronpedia

    INDEX
    Explanations

    mathematical definitions and inclusions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nennen
    -0.08
     traduz
    -0.08
     sane
    -0.08
    _MAX
    -0.08
     odz
    -0.08
    iyan
    -0.07
     xen
    -0.07
     eco
    -0.07
    翻
    -0.07
    certe
    -0.07
    POSITIVE LOGITS
    -inclusive
    0.11
     포함
    0.09
     إليها
    0.09
    Included
    0.08
     સમાવેશ
    0.08
    .Aggreg
    0.08
    .Include
    0.08
    -exclusive
    0.07
    cluded
    0.07
     accueillir
    0.07
    Act Density 0.050%

    No Known Activations