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

    Neuronpedia

    INDEX
    Explanations

    A medida

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Often
    0.85
     Physiology
    0.82
     often
    0.81
    Often
    0.80
    が好き
    0.79
    often
    0.79
     CRUD
    0.78
     quelquefois
    0.77
     Sometimes
    0.75
     વડે
    0.75
    POSITIVE LOGITS
    据悉
    0.95
     تاہم
    0.93
    报道
    0.89
    อย่างไร
    0.88
     AFP
    0.86
    AFP
    0.86
    μφωνα
    0.86
    According
    0.84
    ล่าสุด
    0.84
    報道
    0.82
    Act Density 0.059%

    No Known Activations