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

    Neuronpedia

    INDEX
    Explanations

    language, speech, and comprehension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mắt
    0.44
    CHEAT
    0.43
    在日本
    0.43
    cheek
    0.40
    臀
    0.40
     priorité
    0.38
    raviolet
    0.38
     habitudes
    0.38
    prestations
    0.38
    kä
    0.37
    POSITIVE LOGITS
     comprehension
    0.69
     Language
    0.68
     speech
    0.68
     language
    0.65
     naming
    0.63
     Speech
    0.63
     semantic
    0.58
    Language
    0.56
    Speech
    0.56
     Compre
    0.56
    Act Density 0.015%

    No Known Activations