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

    Neuronpedia

    INDEX
    Explanations

    foreign languages and Arabic words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᓐ
    0.74
    y
    0.72
    ldon
    0.71
    x
    0.69
    v
    0.65
    yum
    0.64
    Ace
    0.63
    ld
    0.62
    g
    0.62
    י
    0.62
    POSITIVE LOGITS
    所有的
    0.73
     உருவாக்க
    0.70
     retros
    0.70
     jednak
    0.69
     matte
    0.69
     गणपति
    0.69
     walnuts
    0.68
     وہاں
    0.68
     fingert
    0.68
     sightings
    0.68
    Act Density 0.001%

    No Known Activations