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

    Neuronpedia

    INDEX
    Explanations

    Roman, LM Studio, Dymatize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ा
    1.03
    a
    0.98
    าม
    0.95
    in
    0.94
     bald
    0.94
    ゙
    0.93
    ่ม
    0.93
     refractive
    0.90
     righteous
    0.90
    вими
    0.90
    POSITIVE LOGITS
    으로써
    1.97
    atically
    1.91
    ática
    1.81
    otive
    1.75
    áticas
    1.72
    ilitary
    1.71
    धील
    1.71
    ático
    1.67
    ühle
    1.66
    endous
    1.59
    Act Density 0.440%

    No Known Activations