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

    Neuronpedia

    INDEX
    Explanations

    4 year old

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     smother
    0.98
     snugly
    0.89
     slapped
    0.89
    at
    0.85
     artery
    0.84
     의한
    0.83
    ducting
    0.82
    ependent
    0.82
     imping
    0.82
     dependent
    0.81
    POSITIVE LOGITS
     वर्षीय
    1.57
    তম
    1.40
    ٪
    1.33
     век
    1.26
     درصد
    1.24
     வய
    1.22
     cents
    1.21
     हजार
    1.21
     процентов
    1.21
     હજાર
    1.15
    Act Density 0.625%

    No Known Activations