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

    Neuronpedia

    INDEX
    Explanations

    traces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     所
    -0.07
     دون
    -0.07
    .grade
    -0.07
     РФ
    -0.07
     AABB
    -0.06
     어느
    -0.06
     퍼
    -0.06
     съ
    -0.06
    upport
    -0.06
     आय
    -0.06
    POSITIVE LOGITS
    created
    0.07
     فشار
    0.07
     placed
    0.07
    ेशन
    0.07
    χώ
    0.06
    processing
    0.06
    gold
    0.06
    DOCTYPE
    0.06
     process
    0.06
    落
    0.06
    Act Density 0.000%

    No Known Activations