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

    Neuronpedia

    INDEX
    Explanations

    html element names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     namun
    0.43
     څرنګوالی
    0.43
    तर
    0.42
     pracy
    0.42
    FTWARE
    0.41
    سال
    0.41
    صب
    0.39
     zakres
    0.39
     toutefois
    0.39
    人文
    0.38
    POSITIVE LOGITS
     clearfix
    0.70
    ">
    0.65
    container
    0.58
    "><
    0.57
    clearfix
    0.55
    \">
    0.53
     container
    0.51
    ui
    0.49
     active
    0.47
     bg
    0.47
    Act Density 0.010%

    No Known Activations