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

    Neuronpedia

    INDEX
    Explanations

    Word endings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Più
    -1.06
     Roskov
    -1.05
     démocr
    -1.02
     normaux
    -1.02
    moins
    -1.01
     avoient
    -1.00
     autorytatywna
    -1.00
     varandra
    -0.98
     quelcon
    -0.97
     szép
    -0.96
    POSITIVE LOGITS
     mor
    0.60
     mo
    0.47
     Mor
    0.44
     gr
    0.43
     ore
    0.41
        
    0.41
     m
    0.41
    ↵
    0.41
    mo
    0.41
    </blockquote>
    0.40
    Act Density 0.041%

    No Known Activations