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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     плю
    -0.07
     Ori
    -0.06
    	this
    -0.06
     фран
    -0.06
     Wid
    -0.06
     sieve
    -0.06
     Tài
    -0.06
     jeszcze
    -0.06
     artery
    -0.06
    _bits
    -0.06
    POSITIVE LOGITS
    ughter
    0.07
    」的
    0.07
     музы
    0.07
    ervices
    0.07
     Snapdragon
    0.07
    zens
    0.06
    adesh
    0.06
     quarterback
    0.06
     біль
    0.06
    .Hidden
    0.06
    Act Density 0.149%

    No Known Activations