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

    Neuronpedia

    INDEX
    Explanations

    asset vs. debt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urb
    0.43
    ictal
    0.42
    nict
    0.41
     martial
    0.41
    alled
    0.40
    icit
    0.40
    ériel
    0.40
    urri
    0.39
    制造
    0.39
    ürm
    0.39
    POSITIVE LOGITS
     atau
    0.49
     Neighbors
    0.47
    紀念
    0.45
     mencionar
    0.44
     sopa
    0.44
     Votre
    0.44
     cedar
    0.44
     Towards
    0.44
     vaya
    0.44
     pagar
    0.43
    Act Density 0.005%

    No Known Activations