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

    Neuronpedia

    INDEX
    Explanations

    Developer Mode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ваших
    0.58
     primeiro
    0.56
     व्यापारी
    0.55
    ют
    0.51
     invari
    0.50
     estup
    0.50
     торго
    0.50
     nutric
    0.50
    เรีย
    0.50
    прия
    0.48
    POSITIVE LOGITS
     Velvet
    0.47
    Ken
    0.47
    á
    0.45
     Sincerely
    0.45
     Socialism
    0.42
    hidupan
    0.42
     L
    0.40
    ToString
    0.40
     Eyes
    0.40
     Manufacture
    0.40
    Act Density 0.002%

    No Known Activations