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

    Neuronpedia

    INDEX
    Explanations

    run in a spiral path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.45
     cosas
    0.45
     puertas
    0.44
     conversión
    0.44
     conversion
    0.42
    ü
    0.42
    otro
    0.41
    ção
    0.40
    otus
    0.40
     defences
    0.39
    POSITIVE LOGITS
     الع
    0.52
    gorod
    0.48
    ಾಲ
    0.48
    준다
    0.47
    ເພດ
    0.47
    anel
    0.46
    린
    0.46
    aign
    0.45
     Adjust
    0.45
    Chen
    0.45
    Act Density 0.002%

    No Known Activations