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
     �
    -0.07
    ường
    -0.06
    のだ
    -0.06
     예
    -0.06
     شکن
    -0.06
    illiseconds
    -0.06
    ――
    -0.06
    urchased
    -0.06
    學院
    -0.06
     CHUNK
    -0.06
    POSITIVE LOGITS
    green
    0.07
     paginator
    0.07
    -<?
    0.06
     highlighted
    0.06
    (Object
    0.06
    !';↵
    0.06
    _orientation
    0.06
    ImGui
    0.06
    serious
    0.06
    cannot
    0.06
    Act Density 0.038%

    No Known Activations