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

    Neuronpedia

    INDEX
    Explanations

    say

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Give
    0.51
     give
    0.47
    give
    0.47
     Give
    0.46
     GIVE
    0.41
    কাহিনী
    0.41
     giving
    0.40
     भेज
    0.39
    ITERATURE
    0.39
     argumentation
    0.38
    POSITIVE LOGITS
     said
    0.75
    said
    0.64
     sagt
    0.59
    說
    0.59
     clarified
    0.57
     says
    0.55
    说
    0.55
     gesagt
    0.53
     Said
    0.52
     säga
    0.52
    Act Density 0.101%

    No Known Activations