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

    Neuronpedia

    INDEX
    Explanations

    lists of numbers and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كانوا
    0.38
     derived
    0.35
     Markov
    0.35
     sitter
    0.35
     ܀
    0.34
     literal
    0.34
     Dank
    0.33
     Mire
    0.32
     couche
    0.32
    ាហ
    0.32
    POSITIVE LOGITS
    វា
    0.44
    वस्था
    0.42
    Storage
    0.38
    Drama
    0.38
    Diversity
    0.38
     ĝi
    0.38
     найбіль
    0.37
    Bulletin
    0.37
    скетбол
    0.37
    śred
    0.37
    Act Density 0.000%

    No Known Activations