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

    Neuronpedia

    INDEX
    Explanations

    added os must updates weekly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    า
    0.46
    ah
    0.45
    πει
    0.42
    想
    0.42
     pixels
    0.41
    ว่า
    0.40
    diameter
    0.40
    In
    0.39
    瓶
    0.39
    [-
    0.38
    POSITIVE LOGITS
     редак
    0.52
    كت
    0.50
     ذریعہ
    0.50
    GEBURTS
    0.49
     велико
    0.49
     semelh
    0.48
    鶉
    0.46
     أق
    0.46
     Конститу
    0.46
     проведен
    0.46
    Act Density 0.001%

    No Known Activations