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

    Neuronpedia

    INDEX
    Explanations

    design foundations, ensure entry, API credentials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Soup
    0.42
    べき
    0.39
    筷
    0.39
     poorer
    0.37
     துற
    0.37
     무료
    0.37
    études
    0.37
     బై
    0.37
    attoo
    0.36
     upstairs
    0.36
    POSITIVE LOGITS
     fraudulently
    0.39
     îng
    0.37
     myös
    0.36
     خفیہ
    0.36
    ホール
    0.35
    дото
    0.35
    鋰
    0.35
    കം
    0.35
    ᆼ
    0.35
     hallar
    0.34
    Act Density 0.004%

    No Known Activations