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

    Neuronpedia

    INDEX
    Explanations

    specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    機制
    0.45
     част
    0.43
    ')[
    0.43
    genden
    0.42
     ২
    0.41
     unfair
    0.41
    鍰
    0.41
    льга
    0.41
    циона
    0.41
     Valletta
    0.40
    POSITIVE LOGITS
    Australian
    0.47
     hỗ
    0.45
     years
    0.44
     puddle
    0.44
     utilisés
    0.44
     Australian
    0.43
     ayudar
    0.43
     utilisée
    0.43
     compatibility
    0.42
     ajudar
    0.42
    Act Density 0.001%

    No Known Activations