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

    Neuronpedia

    INDEX
    Explanations

    factual

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	contentPane
    -0.07
     conveying
    -0.07
    lexible
    -0.07
    ﱠ
    -0.07
    awks
    -0.07
     LY
    -0.07
     piel
    -0.07
    陕西
    -0.07
    愐
    -0.07
    .jd
    -0.07
    POSITIVE LOGITS
    しておく
    0.08
    boost
    0.07
     Qual
    0.07
     большое
    0.07
     zaj
    0.07
     Hydraulic
    0.07
    ATEGORY
    0.07
    셒
    0.07
    symbol
    0.07
     Burg
    0.07
    Act Density 0.002%

    No Known Activations