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

    Neuronpedia

    INDEX
    Explanations

    SVG path commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sucrose
    0.46
     convivial
    0.44
     acyl
    0.44
     estudantes
    0.43
     residentes
    0.41
     prestigio
    0.41
     aprecia
    0.41
     saada
    0.40
     bilangan
    0.39
     cannabin
    0.39
    POSITIVE LOGITS
     then
    0.50
    one
    0.46
    vertical
    0.46
     THEN
    0.45
     થઈ
    0.45
    bottom
    0.44
    ோடு
    0.43
     til
    0.42
    box
    0.42
     '
    0.42
    Act Density 0.025%

    No Known Activations