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

    Neuronpedia

    INDEX
    Explanations

    gold price per unit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Categoria
    0.51
    Renault
    0.46
    氀
    0.43
    ιον
    0.42
    ﻲ
    0.41
     ازيكم
    0.41
     परिवर्तित
    0.41
    >∕</
    0.40
    ﺤ
    0.40
     শিব
    0.40
    POSITIVE LOGITS
     gaps
    0.39
     gấp
    0.38
    0.38
     Gap
    0.38
     Release
    0.38
     varnish
    0.37
     nominations
    0.36
     stop
    0.36
    弥
    0.35
     gas
    0.35
    Act Density 0.001%

    No Known Activations