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

    Neuronpedia

    INDEX
    Explanations

    singular pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ஈடுப
    0.49
     হিন্দুর
    0.49
     moisturizing
    0.47
    ຫ
    0.46
     burl
    0.46
     topologically
    0.45
     adorn
    0.44
     высота
    0.44
     flatter
    0.43
    神社
    0.43
    POSITIVE LOGITS
    news
    0.53
    signed
    0.50
    c
    0.49
    x
    0.47
    tent
    0.45
    p
    0.45
     news
    0.44
    sos
    0.42
     permesso
    0.42
    ‘
    0.41
    Act Density 0.001%

    No Known Activations