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

    Neuronpedia

    INDEX
    Explanations

    html link tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.66
     manus
    0.57
     tiller
    0.55
     placer
    0.53
     papp
    0.52
     transporter
    0.52
     Venezuelan
    0.51
     \
    0.50
     botan
    0.50
     skateboard
    0.50
    POSITIVE LOGITS
    م
    0.81
    ul
    0.77
    Т
    0.69
    ни
    0.64
    যথ
    0.63
    n
    0.62
    н
    0.62
    ЗА
    0.61
     ಹಾಗೂ
    0.61
    НЫ
    0.61
    Act Density 0.001%

    No Known Activations