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

    Neuronpedia

    INDEX
    Explanations

    continue or repeat actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রথমে
    0.93
     zunächst
    0.86
     funzionamento
    0.85
     prélim
    0.81
     সর্বপ্রথম
    0.77
     funcionamento
    0.77
     inicialmente
    0.77
     diretamente
    0.77
     প্রথমেই
    0.77
    最重要的
    0.76
    POSITIVE LOGITS
     repeat
    2.17
     Repeat
    1.92
    Repeat
    1.89
     repeats
    1.84
    repeat
    1.81
     repeated
    1.71
     revisit
    1.68
     repeating
    1.66
     revisiting
    1.55
     повто
    1.53
    Act Density 0.271%

    No Known Activations