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

    Neuronpedia

    INDEX
    Explanations

    fractions less than 1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entr
    -0.08
    个
    -0.07
    노
    -0.07
     कल
    -0.07
    orset
    -0.07
    Eks
    -0.07
    节点
    -0.07
    anee
    -0.07
     synonymous
    -0.07
    =row
    -0.07
    POSITIVE LOGITS
     humilde
    0.09
     consumir
    0.08
    bereich
    0.08
    bereiche
    0.08
     Crossing
    0.08
     звук
    0.08
     Rational
    0.08
     antibiot
    0.08
    терес
    0.08
     Breast
    0.08
    Act Density 0.037%

    No Known Activations