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

    Neuronpedia

    INDEX
    Explanations

    oso

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uft
    -0.07
    ':↵↵
    -0.07
    .coin
    -0.06
     mails
    -0.06
     (@
    -0.06
    Beth
    -0.06
     باش
    -0.06
     Wenn
    -0.06
    	Null
    -0.06
    柄
    -0.06
    POSITIVE LOGITS
     declines
    0.07
     عاما
    0.06
     rhetoric
    0.06
     Commod
    0.06
     enjoying
    0.06
     İmparator
    0.06
     valley
    0.06
    ’util
    0.06
     Records
    0.06
    相信
    0.06
    Act Density 0.035%

    No Known Activations