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

    Neuronpedia

    INDEX
    Explanations

    common word pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ُ
    0.38
     vérité
    0.35
     و
    0.35
     estratégia
    0.34
     étude
    0.33
     strateg
    0.33
     você
    0.33
     vous
    0.33
     intelligente
    0.33
     strategi
    0.32
    POSITIVE LOGITS
    esinin
    0.35
    enapi
    0.32
    })$.
    0.29
    }}$.
    0.29
    ទេ។
    0.29
    umably
    0.29
    umni
    0.28
    ađ
    0.28
    Hfn
    0.28
    ították
    0.28
    Act Density 0.077%

    No Known Activations