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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     جمهوری
    -0.07
    ITT
    -0.07
    .Standard
    -0.07
    -Re
    -0.07
     within
    -0.07
    threads
    -0.07
    question
    -0.06
     Sites
    -0.06
    共和国
    -0.06
    <Data
    -0.06
    POSITIVE LOGITS
     fours
    0.06
    )>>
    0.06
     ={
    0.06
    �
    0.06
     lightly
    0.06
     harbor
    0.06
     Glas
    0.06
    uali
    0.05
     بق
    0.05
     uç
    0.05
    Act Density 0.012%

    No Known Activations