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

    Neuronpedia

    INDEX
    Explanations

    dissapearedworld records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    1.86
    ها
    1.46
    us
    1.39
    até
    1.34
    ai
    1.32
    atay
    1.29
    atanga
    1.27
    ong
    1.25
    ar
    1.20
    ip
    1.20
    POSITIVE LOGITS
    ↵
    1.37
     produz
    1.20
    P
    1.18
    C
    1.13
    H
    1.13
     في
    1.09
    ’
    1.07
     כ
    1.06
     divulg
    1.06
    '
    1.04
    Act Density 0.000%

    No Known Activations