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

    Neuronpedia

    INDEX
    Explanations

    loving relationships and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    1.70
    Karte
    1.61
     Converts
    1.61
     Folgen
    1.61
     arrhythmias
    1.50
    いった
    1.49
    RefreshToken
    1.49
     bleibt
    1.48
     Baiklah
    1.48
    ydi
    1.46
    POSITIVE LOGITS
    l
    2.03
    lardı
    1.70
    lly
    1.64
    ு
    1.61
     ﺍﻟ
    1.57
    lini
    1.57
    dalam
    1.52
    dengan
    1.52
    don
    1.50
    lina
    1.49
    Act Density 0.005%

    No Known Activations