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

    Neuronpedia

    INDEX
    Explanations

    simple descriptions or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abilité
    0.48
    负载
    0.48
     ئەو
    0.48
     кандай
    0.47
    の使用
    0.46
    设
    0.46
    醝
    0.46
     práctico
    0.45
     제시
    0.45
    два
    0.45
    POSITIVE LOGITS
     bestehen
    0.54
     by
    0.47
    ],
    0.44
    }'
    0.44
     for
    0.44
     সড়কের
    0.44
    CREATE
    0.43
    through
    0.42
     buses
    0.42
    zwe
    0.42
    Act Density 0.000%

    No Known Activations