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

    Neuronpedia

    INDEX
    Explanations

    follow-ups or follow-ons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ाइज
    0.73
     shuffling
    0.70
    ualaikum
    0.67
    ถม
    0.67
    Recipes
    0.65
     આમંત્રણ
    0.65
    ці
    0.65
    }]}\
    0.65
     voyageurs
    0.65
    ційних
    0.64
    POSITIVE LOGITS
    aways
    1.19
     offs
    1.18
    away
    1.18
    -
    1.17
    outs
    1.16
    offs
    1.13
    out
    1.12
    up
    1.07
     outs
    1.04
    ‑
    0.95
    Act Density 0.028%

    No Known Activations