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

    Neuronpedia

    INDEX
    Explanations

    faceted, Head, Factor, Step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ための
    1.94
    ებული
    1.90
    пъл
    1.89
    bbox
    1.87
    га
    1.86
    BRUARY
    1.85
     وم
    1.82
     рам
    1.80
     îmb
    1.78
     وتن
    1.77
    POSITIVE LOGITS
     sclerosis
    2.94
     myeloma
    2.89
     vezes
    2.33
    faceted
    2.21
     personalities
    2.19
    ieurs
    2.16
     deles
    2.09
    PubMed
    2.08
     facets
    2.05
    ের
    2.02
    Act Density 0.050%

    No Known Activations