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

    Neuronpedia

    INDEX
    Explanations

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نا
    0.42
    ان
    0.38
     shamb
    0.37
    ก็
    0.35
    ницу
    0.32
    야
    0.32
    ני
    0.32
    ಟರ್
    0.31
     waistband
    0.31
    קר
    0.31
    POSITIVE LOGITS
    }
    0.50
    F
    0.47
    s
    0.46
    ы
    0.43
    r
    0.40
     Dezember
    0.39
    G
    0.39
    <0x0D>
    0.38
    ;}
    0.37
     aprile
    0.36
    Act Density 0.171%

    No Known Activations