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

    Neuronpedia

    INDEX
    Explanations

    know your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Haw
    0.43
     கிர
    0.43
     profesión
    0.42
     otur
    0.39
     profiss
    0.39
     setEmail
    0.38
    翘
    0.37
     haw
    0.36
     prim
    0.36
    няются
    0.36
    POSITIVE LOGITS
    Know
    0.82
     Know
    0.72
     know
    0.70
    know
    0.63
     KNOW
    0.54
     knows
    0.49
     Knowing
    0.49
     知
    0.49
     знать
    0.49
    Зна
    0.48
    Act Density 0.006%

    No Known Activations