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

    Neuronpedia

    INDEX
    Explanations

    particles, accelerated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Deal
    -0.07
    想
    -0.07
    _wifi
    -0.07
    .support
    -0.07
     reveals
    -0.06
    灭
    -0.06
     transition
    -0.06
     انت
    -0.06
    ще
    -0.06
     دهد
    -0.06
    POSITIVE LOGITS
    डर
    0.06
    _IList
    0.06
     mushrooms
    0.06
     

↵
    0.06
    ิงหาคม
    0.06
     مخ
    0.06
    awns
    0.06
    خب
    0.06
     χρή
    0.06
     EditorGUI
    0.06
    Act Density 0.020%

    No Known Activations