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

    Neuronpedia

    INDEX
    Explanations

    Page 1 marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raisons
    0.41
     arco
    0.39
     Slope
    0.36
    ぜ
    0.36
     invester
    0.36
     yatırım
    0.35
     Arco
    0.35
     integrada
    0.35
     ESL
    0.35
     integration
    0.34
    POSITIVE LOGITS
    Guardian
    0.36
    FlaskApp
    0.36
    ဖြင့်
    0.35
    stituting
    0.35
    udarstven
    0.35
    ման
    0.35
     ペット
    0.34
    limiting
    0.34
    chant
    0.33
    或許
    0.33
    Act Density 0.002%

    No Known Activations