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

    Neuronpedia

    INDEX
    Explanations

    names and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atud
    0.34
    ha
    0.33
    ir
    0.33
    hr
    0.33
    ater
    0.31
    al
    0.31
    نا
    0.31
    льним
    0.30
    andering
    0.30
    map
    0.29
    POSITIVE LOGITS
     drows
    0.40
     și
    0.36
     crescita
    0.36
     on
    0.35
     ș
    0.34
     que
    0.34
     e
    0.32
     daisy
    0.32
     cried
    0.32
     congruence
    0.31
    Act Density 0.053%

    No Known Activations