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

    Neuronpedia

    INDEX
    Explanations

    run the script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ",
    0.60
    ，
    0.59
    ،
    0.59
    ',
    0.57
    <0x0D>
    0.50
    ፣
    0.50
     taboo
    0.49
    t
    0.48
    ↵
    0.48
     Barcelone
    0.48
    POSITIVE LOGITS
    Ⴉ
    0.48
    らっしゃ
    0.46
    logging
    0.45
    éal
    0.45
    pple
    0.44
    ॉर्म
    0.43
    dishwasher
    0.43
     Пример
    0.42
     Contains
    0.41
    rapping
    0.41
    Act Density 1.968%

    No Known Activations