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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NP
    -0.07
     есть
    -0.06
    封
    -0.06
     Integer
    -0.06
    结合
    -0.06
     repeated
    -0.06
    _IMPL
    -0.06
    <x
    -0.06
     XY
    -0.06
    .INVALID
    -0.06
    POSITIVE LOGITS
    жу
    0.06
     Soldier
    0.06
    _PW
    0.06
    WidgetItem
    0.06
     usr
    0.06
    นาง
    0.06
     oyuncu
    0.06
     productive
    0.06
    reb
    0.06
    .SetText
    0.06
    Act Density 0.012%

    No Known Activations