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

    Neuronpedia

    INDEX
    Explanations

    alternate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ###↵↵
    -0.07
    θη
    -0.07
    CustomerId
    -0.06
     إي
    -0.06
     결과
    -0.06
    はい
    -0.06
    .foundation
    -0.06
    Hdr
    -0.06
    invoice
    -0.06
    θι
    -0.06
    POSITIVE LOGITS
     проп
    0.07
    artifact
    0.07
    �
    0.07
    (getClass
    0.06
    READING
    0.06
     millet
    0.06
     نمود
    0.06
     naš
    0.06
    )#
    0.06
     фут
    0.06
    Act Density 0.023%

    No Known Activations