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

    Neuronpedia

    INDEX
    Explanations

    code punctuation and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anisot
    0.91
    (/
    0.87
    ⸨
    0.85
    archiw
    0.82
    (-)
    0.80
    Autres
    0.79
     frumo
    0.78
    Therates
    0.78
    спу
    0.78
    Logical
    0.77
    POSITIVE LOGITS
     '
    0.49
    0.48
     a
    0.46
     p
    0.45
     po
    0.45
     an
    0.45
     "
    0.44
    .
    0.43
     tasks
    0.42
     our
    0.42
    Act Density 0.965%

    No Known Activations