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

    Neuronpedia

    INDEX
    Explanations

    phone numbers containing 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ucar
    0.41
     Grease
    0.39
     kart
    0.38
     Croix
    0.38
     celebrated
    0.38
    كبر
    0.38
    協
    0.38
    grand
    0.37
     Giovanni
    0.37
     archipelago
    0.37
    POSITIVE LOGITS
    Successful
    0.51
    สุด
    0.51
    Quite
    0.50
    KeyUp
    0.49
     функций
    0.49
    gulp
    0.48
    Autowired
    0.48
    Sunflower
    0.47
     cukup
    0.47
     può
    0.47
    Act Density 0.014%

    No Known Activations