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

    Neuronpedia

    INDEX
    Explanations

    Gemini.GPT.Alpaca.OpenAI.bing.places.health.doubt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    РА
    0.47
    дру
    0.44
    ვლი
    0.43
    ellini
    0.42
    ``.
    0.42
    Hlav
    0.41
    増加
    0.40
    ере
    0.40
    ellingen
    0.40
     نہایت
    0.40
    POSITIVE LOGITS
     housed
    0.50
     Commercial
    0.47
     (
    0.47
     used
    0.44
     Amarillo
    0.44
     accessible
    0.43
     Willow
    0.43
     might
    0.42
     Quick
    0.42
     commercial
    0.42
    Act Density 0.023%

    No Known Activations