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

    Neuronpedia

    INDEX
    Explanations

    quantities comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻠ
    0.89
     paździer
    0.85
    ков
    0.82
    вы
    0.80
    িন
    0.80
     WHEN
    0.78
     linda
    0.78
    ಂಭ
    0.77
     ונ
    0.77
     לה
    0.76
    POSITIVE LOGITS
    "="
    0.86
    "，
    0.84
    د
    0.81
    ⏹
    0.77
    roje
    0.76
    ται
    0.75
    "("
    0.75
    𝔱
    0.75
    🎙
    0.75
    ഽ
    0.75
    Act Density 0.276%

    No Known Activations