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

    Neuronpedia

    INDEX
    Explanations

    Comparisons, contrasts, technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .video
    -0.07
     meiden
    -0.07
    Pair
    -0.06
     fiction
    -0.06
    479
    -0.06
     Pair
    -0.06
    	MD
    -0.06
     exploitation
    -0.06
    Collection
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    (o
    0.07
    아
    0.07
    网址
    0.07
    Oregon
    0.06
    [Boolean
    0.06
    <y
    0.06
    isay
    0.06
     масс
    0.06
    TriState
    0.06
     ×
    0.06
    Act Density 0.115%

    No Known Activations