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

    Neuronpedia

    INDEX
    Explanations

    origins and continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    म्मे
    0.48
    క్క
    0.45
     allyl
    0.43
    ोन
    0.42
     desg
    0.42
    ണ്ണ
    0.41
     dibut
    0.41
    온
    0.40
    '(
    0.40
    ート
    0.39
    POSITIVE LOGITS
    aný
    0.48
    VITY
    0.47
    CIT
    0.46
    ANU
    0.46
     শতাব্দ
    0.44
    Caution
    0.43
    ŗ
    0.43
    kod
    0.42
    ERS
    0.41
    CLUDES
    0.41
    Act Density 0.001%

    No Known Activations