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

    Neuronpedia

    INDEX
    Explanations

    on a basis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     löyty
    -0.91
    árqu
    -0.91
    gnato
    -0.88
    providedIn
    -0.87
     kertoo
    -0.85
     natomiast
    -0.85
     käyttää
    -0.85
     mukana
    -0.84
    Materiaal
    -0.83
     pysty
    -0.83
    POSITIVE LOGITS
     on
    5.56
     On
    2.30
    On
    2.17
     على
    2.00
     på
    1.72
     ona
    1.70
     на
    1.66
     trên
    1.55
     På
    1.49
    on
    1.41
    Act Density 0.135%

    No Known Activations