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

    Neuronpedia

    INDEX
    Explanations

    who + verb/pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ra
    2.83
    客様
    2.53
    ca
    2.39
    ni
    2.39
    mination
    2.17
    y
    2.11
    nger
    2.06
    le
    2.02
    ters
    1.99
    gi
    1.99
    POSITIVE LOGITS
    ان
    2.77
    ن
    2.58
    ть
    2.48
    ят
    2.38
    त
    2.38
    ل
    2.36
    น
    2.33
    л
    2.27
    谁
    2.23
    นี่
    2.20
    Act Density 0.097%

    No Known Activations