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

    Neuronpedia

    INDEX
    Explanations

    fall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    觅
    -0.08
    imestamp
    -0.08
    槲
    -0.07
    .Reference
    -0.07
    .previous
    -0.07
    儆
    -0.07
    .examples
    -0.07
     Courage
    -0.07
     Wildlife
    -0.07
    -you
    -0.07
    POSITIVE LOGITS
    0.07
    𨱑
    0.07
     Nut
    0.07
    ::~
    0.06
    \$
    0.06
     medida
    0.06
     persu
    0.06
    0.06
    	O
    0.06
     arguing
    0.06
    Act Density 0.011%

    No Known Activations