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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disminuir
    0.55
    प्टेंबर
    0.54
     Ibid
    0.53
     त्यांना
    0.52
    '].'
    0.52
     princípio
    0.51
    +}$,
    0.50
     diariamente
    0.50
     sufrido
    0.50
     shov
    0.49
    POSITIVE LOGITS
    .
    1.04
    ._
    0.82
    .__
    0.78
    .{
    0.75
    ().
    0.73
    .$
    0.68
    .<
    0.68
    ٫
    0.67
    .*
    0.64
    .___
    0.61
    Act Density 0.265%

    No Known Activations