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

    Neuronpedia

    INDEX
    Explanations

    citations in text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     துணை
    0.43
     postaci
    0.40
     barang
    0.40
    器件
    0.39
     قاسمی
    0.38
     jeweler
    0.38
    वार
    0.38
     dorado
    0.38
    université
    0.37
     levantar
    0.37
    POSITIVE LOGITS
     sens
    0.66
    sens
    0.59
     Sens
    0.55
    Sens
    0.54
     Sense
    0.50
     सेंस
    0.47
    Sense
    0.45
     sense
    0.45
     حس
    0.43
     सें
    0.43
    Act Density 0.000%

    No Known Activations