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

    Neuronpedia

    INDEX
    Explanations

    -Saharan

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DHS
    -0.07
    andr
    -0.07
     holding
    -0.07
    槐
    -0.07
    不该
    -0.07
    enguin
    -0.07
     doing
    -0.07
    )])
    -0.06
    ując
    -0.06
     closes
    -0.06
    POSITIVE LOGITS
     material
    0.07
    	SP
    0.07
    かもしれ
    0.07
     Vig
    0.07
     spokes
    0.07
     unreachable
    0.06
    被困
    0.06
    .addButton
    0.06
    🤭
    0.06
     العرا
    0.06
    Act Density 0.001%

    No Known Activations