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

    Neuronpedia

    INDEX
    Explanations

    former

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     niños
    -0.07
    مر
    -0.07
    USD
    -0.07
    	bs
    -0.07
    届
    -0.07
    ение
    -0.06
    ены
    -0.06
    子
    -0.06
     pers
    -0.06
     nhiên
    -0.06
    POSITIVE LOGITS
     crawler
    0.08
    "){
    0.08
    יצע
    0.08
     phenomenal
    0.08
    flammatory
    0.07
    "]);↵
    0.07
    okableCall
    0.07
    findFirst
    0.07
     Dancing
    0.07
    [
    0.07
    Act Density 0.010%

    No Known Activations