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

    Neuronpedia

    INDEX
    Explanations

    Clear Request, told me, days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    am
    0.52
    on
    0.50
     x
    0.46
     budete
    0.44
    cell
    0.44
    Right
    0.44
    C
    0.44
    Q
    0.43
    াকৃতিক
    0.43
     yer
    0.42
    POSITIVE LOGITS
     शब्द
    0.47
    ᄊ
    0.46
     potentialities
    0.46
    ད་
    0.43
    出来ます
    0.43
     milieux
    0.43
    麥
    0.43
    ล้ว
    0.42
    螻
    0.42
    ང་
    0.41
    Act Density 0.001%

    No Known Activations