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

    Neuronpedia

    INDEX
    Explanations

    requires or involves actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icina
    0.48
     долларов
    0.47
     удобно
    0.46
     вле
    0.46
     температура
    0.46
    лу
    0.45
     идеально
    0.45
     производи
    0.45
    EMAIL
    0.45
     топлива
    0.44
    POSITIVE LOGITS
     gravid
    0.50
    🧒
    0.46
     pregnancies
    0.46
     zależ
    0.44
     obdob
    0.44
     střed
    0.43
    د
    0.43
     civilisation
    0.42
     ferrugineux
    0.42
    بعض
    0.42
    Act Density 0.015%

    No Known Activations