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

    Neuronpedia

    INDEX
    Explanations

    outlining evolving digital landscape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.69
    t
    0.62
    0.54
     \
    0.51
    ID
    0.51
    H
    0.50
    AT
    0.50
    Y
    0.49
    U
    0.48
    St
    0.47
    POSITIVE LOGITS
    লিত
    0.55
    생활
    0.54
    storeItem
    0.54
    спорт
    0.53
    ះ
    0.53
    сини
    0.52
     malice
    0.51
    ጮ
    0.51
    쎌
    0.51
     marchandises
    0.50
    Act Density 0.001%

    No Known Activations