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

    Neuronpedia

    INDEX
    Explanations

    programming code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -​
    0.43
     Dernière
    0.41
     Grâce
    0.41
     À
    0.40
    迸
    0.39
     Cál
    0.38
     Développement
    0.38
     Además
    0.37
     सूर्
    0.36
     Martín
    0.36
    POSITIVE LOGITS
    ref
    0.45
    int
    0.45
    ("",
    0.45
    (),
    0.44
    name
    0.42
    conn
    0.41
    )$;
    0.39
    uint
    0.39
    parseInt
    0.39
    atoi
    0.39
    Act Density 0.012%

    No Known Activations