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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.46
    ad
    0.40
    ר
    0.38
    r
    0.37
     BasicContainer
    0.36
     FabD
    0.34
    ת
    0.34
    onn
    0.34
    tion
    0.34
    to
    0.33
    POSITIVE LOGITS
    ?”
    0.43
    س
    0.43
    ?
    0.43
    {
    0.41
    لي
    0.39
    িগ্ন
    0.38
    ق
    0.37
    RA
    0.37
    κι
    0.36
    ()?
    0.36
    Act Density 3.632%

    No Known Activations