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

    Neuronpedia

    INDEX
    Explanations

    guides and tutorials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Facts
    0.90
     facts
    0.80
     trivia
    0.79
     तथ
    0.79
     Interactive
    0.78
    facts
    0.77
    daftar
    0.75
     Официа
    0.75
    官方
    0.74
     புள்ள
    0.73
    POSITIVE LOGITS
    combination
    0.65
    incre
    0.65
    resulting
    0.62
     আরোপ
    0.62
     influencing
    0.62
    spreading
    0.61
     cleaved
    0.60
     erecting
    0.60
    教學
    0.59
     prevailed
    0.59
    Act Density 0.142%

    No Known Activations