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

    Neuronpedia

    INDEX
    Explanations

    numbers and 3D

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ignoring
    0.37
     Ignore
    0.36
     للمع
    0.35
     என்பது
    0.34
     detract
    0.32
    </h2>
    0.30
    脓
    0.29
     Directions
    0.29
     Studying
    0.29
    #[
    0.29
    POSITIVE LOGITS
    six
    0.57
    three
    0.57
     six
    0.55
    five
    0.54
     trois
    0.52
    eight
    0.51
     twelve
    0.51
     three
    0.51
     five
    0.51
     šest
    0.50
    Act Density 0.269%

    No Known Activations