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

    Neuronpedia

    INDEX
    Explanations

    more, less, faster, fewer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    穰
    0.45
    CATEG
    0.42
     статье
    0.42
    uttosto
    0.42
     HTTPException
    0.42
     pravo
    0.42
    hankelijk
    0.41
    ினால்
    0.41
    reet
    0.40
    ెంబ
    0.40
    POSITIVE LOGITS
     more
    1.76
     fewer
    1.66
     stronger
    1.56
     более
    1.52
     less
    1.52
     יותר
    1.51
     lebih
    1.50
     daha
    1.44
     უფრო
    1.44
     harder
    1.43
    Act Density 0.333%

    No Known Activations