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

    Neuronpedia

    INDEX
    Explanations

    materials challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     проду
    0.45
     മുതൽ
    0.42
     Loans
    0.41
     Callahan
    0.41
     philosophies
    0.41
    ಃ
    0.41
    hauer
    0.40
     LITERATURE
    0.40
     Variable
    0.39
     littérature
    0.39
    POSITIVE LOGITS
    assuming
    0.46
    combine
    0.44
    airport
    0.44
     assuming
    0.41
    tele
    0.41
    unknown
    0.39
    Airport
    0.39
    assume
    0.39
    fluor
    0.39
     assumes
    0.38
    Act Density 0.005%

    No Known Activations