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

    Neuronpedia

    INDEX
    Explanations

    look

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     +(
    -0.07
     dead
    -0.07
    迎
    -0.06
    	and
    -0.06
     desn
    -0.06
    λί
    -0.06
    zego
    -0.06
     leth
    -0.06
     nestled
    -0.06
     шир
    -0.06
    POSITIVE LOGITS
     Dias
    0.07
     Discrim
    0.07
    ุตสาห
    0.06
    postal
    0.06
    .topic
    0.06
     impression
    0.06
    _TRANSFER
    0.06
     Coupe
    0.06
    /gen
    0.06
    _large
    0.06
    Act Density 0.013%

    No Known Activations