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

    Neuronpedia

    INDEX
    Explanations

    Hebrew language and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     completely
    1.16
     blazing
    1.14
     nymph
    1.13
     patterned
    1.10
     providing
    1.08
     collaborated
    1.07
     people
    1.07
     dearest
    1.06
     crea
    1.06
     seasoned
    1.06
    POSITIVE LOGITS
     ק
    2.33
     ש
    2.24
     מ
    2.15
     הש
    2.11
     המ
    2.08
     ר
    2.06
     ג
    2.06
     פ
    2.05
     של
    2.05
     א
    2.03
    Act Density 0.005%

    No Known Activations