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

    Neuronpedia

    INDEX
    Explanations

    яккак"""

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    अधिकांश
    0.65
     verwenden
    0.64
     foodservice
    0.61
     erstellt
    0.60
     denominado
    0.60
    এছ
    0.60
     angiogenic
    0.60
     incrementar
    0.60
     psychosocial
    0.59
     denominada
    0.58
    POSITIVE LOGITS
     за
    0.98
     у
    0.89
     не
    0.86
     с
    0.84
     ду
    0.84
     жа
    0.84
     на
    0.83
     по
    0.81
     страш
    0.81
     люби
    0.80
    Act Density 0.044%

    No Known Activations