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

    Neuronpedia

    INDEX
    Explanations

    international language markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bitOp
    1.38
    🕘
    1.37
    <unused1219>
    1.34
    hatiti
    1.34
    🕔
    1.34
    🚞
    1.33
    attho
    1.33
    icheskoj
    1.33
    tBleStatus
    1.32
    👲
    1.32
    POSITIVE LOGITS
    1.57
     (
    1.52
     [
    1.20
     -
    1.15
    ↵
    1.15
    ↵↵
    1.11
    :
    1.10
      
    1.08
     The
    1.07
     On
    1.05
    Act Density 0.026%

    No Known Activations