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

    Neuronpedia

    INDEX
    Explanations

    DuPont, Dow, 3M

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (&(*
    0.41
     सिद्धार्थ
    0.38
     pabbaj
    0.38
     przes
    0.38
    Group
    0.38
     Sumo
    0.37
     Sketch
    0.37
    Sketch
    0.37
     SCA
    0.37
     controlado
    0.37
    POSITIVE LOGITS
     DuPont
    0.99
     Dupont
    0.88
     dup
    0.83
    Dup
    0.81
    dup
    0.76
     Dow
    0.72
    Dow
    0.63
     Dup
    0.62
     Teflon
    0.61
     Nemours
    0.60
    Act Density 0.002%

    No Known Activations