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

    Neuronpedia

    INDEX
    Explanations

    numbers and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     множе
    0.39
     Multiple
    0.39
    мії
    0.36
    ="#"><
    0.35
    μών
    0.35
     त्व
    0.34
     interceptions
    0.34
     ADR
    0.33
    сро
    0.33
    ҳо
    0.33
    POSITIVE LOGITS
     thirty
    0.98
    几年
    0.97
     fifteen
    0.96
     डेढ़
    0.96
     десять
    0.94
     twenty
    0.94
     ten
    0.92
    十年
    0.91
     몇
    0.89
     quinze
    0.87
    Act Density 0.105%

    No Known Activations