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

    Neuronpedia

    INDEX
    Explanations

    initiation of actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एकदम
    0.54
     absolv
    0.48
     plunge
    0.48
     four
    0.48
     satu
    0.48
     quatro
    0.47
     पूर्ण
    0.46
     tetap
    0.46
    مرار
    0.46
     był
    0.45
    POSITIVE LOGITS
     empiezan
    0.64
     begins
    0.61
     comienzan
    0.61
     Begins
    0.59
     Begin
    0.54
     начинает
    0.54
    就开始
    0.54
     Slowly
    0.53
     began
    0.52
     начну
    0.50
    Act Density 0.105%

    No Known Activations