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

    Neuronpedia

    INDEX
    Explanations

    .com urls and internet links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     |
    0.51
    бил
    0.47
    |(
    0.46
     |\
    0.45
    +{
    0.42
    "_
    0.41
     noy
    0.41
     strop
    0.40
     executive
    0.40
    ào
    0.39
    POSITIVE LOGITS
    沨
    0.73
    ське
    0.73
     તેના
    0.73
     ;-)
    0.70
     Bangla
    0.70
     Carpathians
    0.69
     परमाण
    0.69
     റിപ്പോ
    0.67
    __":
    0.66
     :-)
    0.66
    Act Density 0.808%

    No Known Activations