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

    Neuronpedia

    INDEX
    Explanations

    ever experienced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تخ
    0.54
    Tensor
    0.53
    ۰۰
    0.53
    री
    0.52
    acion
    0.52
    mıştı
    0.51
    tumor
    0.51
    iros
    0.51
     Goddess
    0.51
     Motors
    0.50
    POSITIVE LOGITS
    see
    0.63
     news
    0.61
    See
    0.61
     see
    0.60
     sees
    0.59
     pointB
    0.58
     mendengar
    0.58
     interleukin
    0.55
     দেখে
    0.55
    見
    0.54
    Act Density 0.001%

    No Known Activations