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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     serii
    0.69
     ৯০
    0.68
    intosh
    0.66
    টাল
    0.66
    ifai
    0.65
    ineas
    0.65
    notification
    0.64
     सुल
    0.63
    칫
    0.62
     Khalil
    0.62
    POSITIVE LOGITS
     auß
    0.66
    ++,
    0.65
    водит
    0.63
    bts
    0.62
     REPLACE
    0.61
    ettivo
    0.61
    emakers
    0.61
    ير
    0.60
    ++;//
    0.59
    倉
    0.59
    Act Density 0.102%

    No Known Activations