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

    Neuronpedia

    INDEX
    Explanations

    code syntax and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    şiktaş
    0.42
    ッシング
    0.40
    覦
    0.39
    ەل
    0.39
     répondre
    0.38
    cendo
    0.38
    tudo
    0.38
     évo
    0.37
     disrespectful
    0.37
     शरी
    0.37
    POSITIVE LOGITS
    cl
    0.56
    cc
    0.52
    ll
    0.51
     |
    0.50
    cr
    0.48
    l
    0.48
    ccccc
    0.47
    C
    0.47
    c
    0.46
     c
    0.45
    Act Density 0.000%

    No Known Activations