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

    Neuronpedia

    INDEX
    Explanations

    list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सू
    0.52
    ča
    0.50
    ಪಟ್ಟ
    0.49
     जानकारी
    0.44
     темати
    0.44
     सत्य
    0.44
     screwdriver
    0.43
    стен
    0.43
    isini
    0.43
     மேற்கொள்ள
    0.43
    POSITIVE LOGITS
     and
    0.56
    ה
    0.54
    私
    0.50
    Π
    0.49
     not
    0.49
     coun
    0.48
    3
    0.47
    К
    0.47
    단
    0.47
    今
    0.46
    Act Density 0.005%

    No Known Activations