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

    Neuronpedia

    INDEX
    Explanations

    phrase "here's a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ؛
    0.34
    óis
    0.33
    صله
    0.32
    لو
    0.31
    ار
    0.30
    جز
    0.30
    ophyte
    0.30
     gets
    0.30
     ={
    0.29
     باشد
    0.29
    POSITIVE LOGITS
     a
    0.57
     an
    0.45
     some
    0.45
     μια
    0.39
     several
    0.39
    一些
    0.38
    some
    0.38
     bazı
    0.37
     néhány
    0.36
     ένα
    0.36
    Act Density 0.015%

    No Known Activations