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

    Neuronpedia

    INDEX
    Explanations

    timing and delays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    py
    0.48
     በቀ
    0.41
    简洁
    0.41
     Simplify
    0.41
    材质
    0.40
    >`
    0.40
    yu
    0.40
     సరి
    0.40
     contemporaneous
    0.39
     momentary
    0.39
    POSITIVE LOGITS
     onset
    0.64
     gratification
    0.61
     arriver
    0.58
     delay
    0.55
     llegada
    0.55
     chegada
    0.55
     respuesta
    0.54
     delayed
    0.54
     délais
    0.54
     başlayan
    0.53
    Act Density 0.196%

    No Known Activations