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

    Neuronpedia

    INDEX
    Explanations

    carbon dioxide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.83
     valamint
    0.75
    1
    0.69
     "")
    0.68
    2
    0.67
     illetve
    0.67
    _)
    0.66
    3
    0.65
     czyli
    0.64
    5
    0.63
    POSITIVE LOGITS
    Với
    0.67
     અને
    0.60
     आणि
    0.60
     अपने
    0.59
    和
    0.59
     and
    0.58
     at
    0.58
     in
    0.58
     و
    0.58
    Интернет
    0.57
    Act Density 2.277%

    No Known Activations