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

    Neuronpedia

    INDEX
    Explanations

    creating websites optimized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avian
    0.47
    ampu
    0.44
     unil
    0.43
    oum
    0.42
    avamo
    0.42
    quement
    0.41
    ეგის
    0.41
    on
    0.41
    ons
    0.41
    annya
    0.41
    POSITIVE LOGITS
     разговор
    0.53
     spineItem
    0.48
    รอง
    0.48
    指针
    0.48
     बेच
    0.47
     разрешения
    0.46
     حل
    0.46
    不
    0.46
     derrot
    0.46
     четыре
    0.45
    Act Density 0.002%

    No Known Activations