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

    Neuronpedia

    INDEX
    Explanations

    people and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    their
    0.43
    他们的
    0.39
     качестве
    0.38
     njihov
    0.38
    เช่น
    0.37
     их
    0.36
    他們的
    0.36
     whose
    0.35
     their
    0.35
     thei
    0.34
    POSITIVE LOGITS
     تلاش
    0.33
    pl
    0.32
     attempt
    0.31
    ing
    0.31
     attempts
    0.31
     bedrijven
    0.31
     de
    0.30
     enterprises
    0.30
     Leute
    0.29
    ickets
    0.29
    Act Density 0.050%

    No Known Activations