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

    Neuronpedia

    INDEX
    Explanations

    limitations and boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不仅仅
    0.45
     actually
    0.41
    据说
    0.40
     nejen
    0.40
    不仅
    0.40
    一定的
    0.39
    伦敦
    0.39
     بالفعل
    0.39
     iako
    0.39
     aufgel
    0.38
    POSITIVE LOGITS
     contradictory
    0.44
     applications
    0.42
     സാഹചര്യ
    0.42
     unreachable
    0.42
    nymi
    0.41
     conspiracies
    0.41
    spiel
    0.41
     gadgets
    0.41
     unattainable
    0.41
    obtain
    0.40
    Act Density 0.002%

    No Known Activations