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

    Neuronpedia

    INDEX
    Explanations

    simply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Al
    -0.07
    RIA
    -0.06
     reinterpret
    -0.06
     реги
    -0.06
    cli
    -0.06
     міль
    -0.06
    god
    -0.06
    	dist
    -0.06
    -world
    -0.06
    řad
    -0.06
    POSITIVE LOGITS
    >({
    0.07
    (chart
    0.06
     došlo
    0.06
     Leave
    0.06
     Buf
    0.06
    ",{
    0.06
     QMap
    0.06
     Sext
    0.06
     paperwork
    0.06
     görül
    0.06
    Act Density 0.010%

    No Known Activations