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

    Neuronpedia

    INDEX
    Explanations

    technical papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ağa
    -0.07
     Hancock
    -0.07
     sonu
    -0.06
     Slov
    -0.06
     kaz
    -0.06
    .decoder
    -0.06
    ioxide
    -0.06
     حسين
    -0.06
     vyrá
    -0.06
     předsed
    -0.06
    POSITIVE LOGITS
     verge
    0.06
    睡
    0.06
    	input
    0.06
     german
    0.06
    ność
    0.06
    Btn
    0.06
     llam
    0.06
    launch
    0.06
    Documents
    0.06
     jewish
    0.06
    Act Density 0.000%

    No Known Activations