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

    Neuronpedia

    INDEX
    Explanations

    look around you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entice
    0.61
    䢙
    0.51
     respond
    0.47
     gateways
    0.45
     indonesia
    0.45
    ambique
    0.44
     ಲ
    0.44
     starg
    0.44
    ucapkan
    0.44
    onesia
    0.43
    POSITIVE LOGITS
    س
    0.58
    ס
    0.56
    ه
    0.46
    امد
    0.46
    ج
    0.45
    Caps
    0.43
    ADES
    0.43
    电脑
    0.42
    ص
    0.42
    ี
    0.42
    Act Density 0.002%

    No Known Activations