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

    Neuronpedia

    INDEX
    Explanations

    April

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    形式
    -0.06
    plx
    -0.06
    대학교
    -0.06
     بد
    -0.06
     правда
    -0.06
     Graduate
    -0.06
    تك
    -0.06
    奶
    -0.06
    τερο
    -0.05
     addButton
    -0.05
    POSITIVE LOGITS
     Drink
    0.07
    Expiration
    0.07
     Heap
    0.06
    _max
    0.06
    .Chrome
    0.06
     charms
    0.06
    Dispose
    0.06
    _utf
    0.06
     ')↵↵
    0.06
    prop
    0.06
    Act Density 0.015%

    No Known Activations