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

    Neuronpedia

    INDEX
    Explanations

    months and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ב
    0.38
    ד
    0.36
    מ
    0.35
    b
    0.35
    mith
    0.34
    י
    0.33
     אחר
    0.33
    x
    0.33
     että
    0.32
    ล
    0.32
    POSITIVE LOGITS
    ről
    0.30
    -}
    0.30
    }',
    0.29
    ра
    0.29
    見
    0.28
    -}$
    0.27
    SEASON
    0.26
    ᅬ
    0.26
    forName
    0.26
     Dienstag
    0.25
    Act Density 0.180%

    No Known Activations