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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and contrasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.34
    "،
    0.29
    ”،
    0.28
    0.28
     ਕ
    0.27
     zariaden
    0.26
    ।
    0.25
    '،
    0.25
     خپل
    0.24
     κατα
    0.24
    POSITIVE LOGITS
     लेकिन
    0.39
     или
    0.36
    but
    0.36
     and
    0.36
    หรือ
    0.34
     क्योंकि
    0.34
     but
    0.33
     आणि
    0.33
     కానీ
    0.33
     અને
    0.33
    Act Density 0.815%

    No Known Activations