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

    Neuronpedia

    INDEX
    Explanations

    splits into, session key, visit this, attention grabbing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ే
    0.68
    ின்
    0.66
    ால்
    0.64
    MA
    0.63
    ALSO
    0.61
    Ainsi
    0.61
    आती
    0.61
     jeopard
    0.59
    Pokud
    0.59
    Ś
    0.59
    POSITIVE LOGITS
    с
    0.73
    к
    0.68
    м
    0.68
    n
    0.66
    но
    0.63
    1
    0.62
    ม
    0.60
    եցին
    0.60
    ک
    0.60
    ان
    0.59
    Act Density 0.000%

    No Known Activations