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

    Neuronpedia

    INDEX
    Explanations

    applications, campaign, server, publisher

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یاء
    0.52
     காவல்
    0.46
     önemlidir
    0.45
    WeakTable
    0.45
     મહત્વ
    0.45
     కీలక
    0.44
     wichtigen
    0.44
    перыі
    0.44
    定理
    0.43
    riminating
    0.43
    POSITIVE LOGITS
     purchased
    0.53
    6
    0.52
     marijuana
    0.52
     pod
    0.50
    8
    0.50
     commercial
    0.49
     ³
    0.48
     a
    0.46
     marketed
    0.45
     km
    0.45
    Act Density 0.007%

    No Known Activations