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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cp
    -0.07
    =tmp
    -0.06
    (pr
    -0.06
     pm
    -0.06
    (dp
    -0.06
    .loc
    -0.06
    avenport
    -0.06
    (section
    -0.06
    чила
    -0.06
     argv
    -0.06
    POSITIVE LOGITS
    alm
    0.07
     Middle
    0.07
     çift
    0.06
     آنچه
    0.06
    thal
    0.06
    _dual
    0.06
     conseils
    0.06
    ieties
    0.06
    럴
    0.06
     keer
    0.06
    Act Density 0.001%

    No Known Activations