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

    Neuronpedia

    INDEX
    Explanations

    multilingual or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ні
    0.58
    ных
    0.58
    ной
    0.55
    вни
    0.51
     Door
    0.50
     Direction
    0.50
     Unemployment
    0.50
    لك
    0.49
     Vuitton
    0.49
     Keeping
    0.48
    POSITIVE LOGITS
    0
    0.49
    isati
    0.48
    염
    0.46
     બો
    0.45
    Hola
    0.43
     aggiunto
    0.42
    arin
    0.41
    cluso
    0.41
    Agora
    0.41
    site
    0.41
    Act Density 0.000%

    No Known Activations