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

    Neuronpedia

    INDEX
    Explanations

    iPhone descriptions and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.96
    ığı
    0.93
    ک
    0.88
    ,[
    0.86
     (
    0.84
    л
    0.82
    ties
    0.81
     одна
    0.81
     सहमति
    0.81
     cenderung
    0.79
    POSITIVE LOGITS
    ă
    0.93
    大脑
    0.89
    .
    0.86
    ați
    0.82
    ü
    0.82
    n
    0.81
    do
    0.75
    大陸
    0.75
    rů
    0.73
    한
    0.72
    Act Density 0.003%

    No Known Activations