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

    Neuronpedia

    INDEX
    Explanations

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sécrétion
    0.13
     condenser
    0.13
     روغن
    0.13
    クロマト
    0.13
    餃
    0.13
    脂肪
    0.12
    PERATURE
    0.12
    THAT
    0.12
    ’
    0.12
    ٺ
    0.12
    POSITIVE LOGITS
    ↵
    0.15
     in
    0.12
    ish
    0.12
    iş
    0.12
    um
    0.12
    informat
    0.12
    ed
    0.11
    ates
    0.11
    ef
    0.11
    🎉
    0.11
    Act Density 0.475%

    No Known Activations