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

    Neuronpedia

    INDEX
    Explanations

    zero to Spanish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Neutral
    0.37
    VO
    0.37
    ił
    0.36
    ảo
    0.35
    ็ว
    0.35
     Cosmetics
    0.35
    导
    0.35
     illumination
    0.34
    PLUS
    0.34
    கி
    0.33
    POSITIVE LOGITS
     buddhav
    0.46
     meriye
    0.45
     assigns
    0.44
    utm
    0.44
    0.43
     tanha
    0.41
    }}^{*}
    0.40
     assign
    0.40
     거예요
    0.40
    зир
    0.40
    Act Density 0.001%

    No Known Activations