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

    Neuronpedia

    INDEX
    Explanations

    large selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prototype
    0.39
    apanicolaou
    0.38
     ちゃっ
    0.38
     divert
    0.37
     archetype
    0.37
    multif
    0.37
    上位
    0.36
     maximally
    0.36
     datatype
    0.36
    amble
    0.35
    POSITIVE LOGITS
     selection
    1.83
    selection
    1.65
     Selection
    1.62
     variety
    1.60
     variedade
    1.55
     ассорти
    1.53
    Selection
    1.52
     Auswahl
    1.51
     assortment
    1.47
     selections
    1.41
    Act Density 0.031%

    No Known Activations