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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hammered
    -0.07
     других
    -0.07
     معمول
    -0.06
     Ded
    -0.06
    İstanbul
    -0.06
    Those
    -0.06
    öst
    -0.06
     jQuery
    -0.06
     nedenle
    -0.06
     الدولة
    -0.06
    POSITIVE LOGITS
     cv
    0.06
    nsic
    0.06
     emot
    0.06
    -fin
    0.06
    pick
    0.06
     dmg
    0.06
    ็จ
    0.06
    vac
    0.06
    ric
    0.06
     któ
    0.06
    Act Density 0.081%

    No Known Activations