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

    Neuronpedia

    INDEX
    Explanations

    times of day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ignor
    0.61
     true
    0.58
     implic
    0.55
     존재
    0.55
    が存在
    0.54
     et
    0.52
     impost
    0.51
     dispar
    0.51
     hypoc
    0.51
     falsehood
    0.51
    POSITIVE LOGITS
    lunch
    0.92
     lunch
    0.91
    晚餐
    0.90
     दोपहर
    0.89
    evening
    0.88
     afternoon
    0.86
     journée
    0.83
     photoshoot
    0.81
    中午
    0.80
     evening
    0.79
    Act Density 0.027%

    No Known Activations