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

    Neuronpedia

    INDEX
    Explanations

    lists and bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अभियान
    0.45
     humain
    0.39
     समुद्र
    0.38
    ಶಾ
    0.37
     kasnije
    0.37
     posteriores
    0.37
     humana
    0.36
    ydi
    0.36
    campaign
    0.36
     starb
    0.36
    POSITIVE LOGITS
     compact
    0.39
     perceived
    0.39
    டோ
    0.39
    č
    0.38
    ފައި
    0.37
    WER
    0.37
    需要
    0.36
     sizeof
    0.36
    现在的
    0.36
    开口
    0.36
    Act Density 0.002%

    No Known Activations