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

    Neuronpedia

    INDEX
    Explanations

    to express, and dismiss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ocyte
    0.51
    quele
    0.48
    ize
    0.47
    ađ
    0.46
    ipine
    0.46
    imine
    0.45
    ese
    0.44
    erian
    0.43
     ayatan
    0.43
    inburgh
    0.43
    POSITIVE LOGITS
     искусства
    0.46
    RENT
    0.43
    伀
    0.42
     disbanded
    0.41
     যা
    0.41
    ב
    0.41
    輔
    0.41
    帼
    0.40
     auss
    0.40
    咅
    0.39
    Act Density 0.000%

    No Known Activations