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

    Neuronpedia

    INDEX
    Explanations

    (and why)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ម្លៃ
    0.44
    cijas
    0.44
    ร้อม
    0.42
    his
    0.42
    tareas
    0.42
    itchfield
    0.42
    that
    0.41
    ალური
    0.41
    सास
    0.41
    夥
    0.41
    POSITIVE LOGITS
     emitted
    0.52
    )
    0.50
     neurom
    0.49
     dialed
    0.48
     leaked
    0.47
     issued
    0.47
     consulted
    0.47
    ↵
    0.47
     dispatched
    0.47
     âm
    0.47
    Act Density 0.001%

    No Known Activations