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

    Neuronpedia

    INDEX
    Explanations

    tuk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    0.45
     vector
    0.41
     fillets
    0.41
    वार
    0.40
    aterial
    0.39
    ัต
    0.38
     typedef
    0.38
     обеспечения
    0.37
     retired
    0.37
     screws
    0.36
    POSITIVE LOGITS
    Order
    0.42
     aude
    0.41
    QUOTE
    0.40
     filoz
    0.40
     eme
    0.40
     இருந்து
    0.39
     реши
    0.39
    وبه
    0.39
     ORDER
    0.39
     juge
    0.39
    Act Density 0.012%

    No Known Activations