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

    Neuronpedia

    INDEX
    Explanations

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lament
    -0.07
     Programming
    -0.07
     computational
    -0.07
    NewItem
    -0.07
     Maint
    -0.07
    bstract
    -0.07
     Mining
    -0.07
    .Sm
    -0.07
    Prog
    -0.07
    AV
    -0.07
    POSITIVE LOGITS
    	export
    0.06
    (",");↵
    0.06
    	total
    0.06
    ,$_
    0.06
    veç
    0.06
    论文
    0.06
     },{↵
    0.06
    ื
    0.06
    accumulator
    0.06
     kell
    0.06
    Act Density 0.018%

    No Known Activations