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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions like `*` and `)`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     යන
    0.73
     വ്യ
    0.68
     глаза
    0.66
     වඩා
    0.64
     radiological
    0.63
     또는
    0.61
    TextAlign
    0.59
    Lep
    0.59
     kaug
    0.59
     හෝ
    0.58
    POSITIVE LOGITS
    फ्ट
    0.76
    rifice
    0.73
     ingenious
    0.73
     gallant
    0.73
     witty
    0.72
     cunning
    0.72
    writer
    0.71
    গকে
    0.69
    没有什么
    0.67
     አለበት
    0.67
    Act Density 0.000%

    No Known Activations