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

    Neuronpedia

    INDEX
    Explanations

    specific information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Anyone
    0.44
    Gray
    0.44
    anyone
    0.43
    forum
    0.42
    plans
    0.41
     йил
    0.41
     blunt
    0.41
    हिट
    0.41
    Countries
    0.40
    edition
    0.38
    POSITIVE LOGITS
    说法
    0.41
     frecu
    0.39
    बाब
    0.39
     linearity
    0.39
     confortable
    0.39
     грамо
    0.38
     ваго
    0.38
     Aussage
    0.38
     আই
    0.37
    蘋
    0.37
    Act Density 0.003%

    No Known Activations