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

    Neuronpedia

    INDEX
    Explanations

    image

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depot
    -0.07
    Endpoints
    -0.07
    اران
    -0.07
    ايت
    -0.07
    уск
    -0.07
     حوزه
    -0.07
    満
    -0.07
     bast
    -0.07
     scape
    -0.06
    år
    -0.06
    POSITIVE LOGITS
    <|eot_id|>
    0.07
    _OW
    0.06
    	utils
    0.06
     continuous
    0.06
    aporan
    0.05
     exercised
    0.05
    .cum
    0.05
    PRETTY
    0.05
    Professional
    0.05
     =>
    0.05
    Act Density 0.008%

    No Known Activations