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

    Neuronpedia

    INDEX
    Explanations

    break down into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     הז
    0.54
     coefficient
    0.48
    ተኛ
    0.48
     זה
    0.47
     restaurant
    0.45
    OS
    0.45
     이것
    0.45
     juntas
    0.44
     benefactor
    0.44
     manufacturer
    0.44
    POSITIVE LOGITS
    مس
    0.70
     možete
    0.65
    čke
    0.64
    c
    0.63
    非常
    0.60
    à
    0.59
    g
    0.59
    على
    0.58
    كبر
    0.58
    മ
    0.56
    Act Density 0.840%

    No Known Activations