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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ":"
    -0.06
     emoji
    -0.06
     </
    -0.06
    '"
    -0.06
     mine
    -0.06
    clients
    -0.06
     influenza
    -0.06
    ieme
    -0.06
    succ
    -0.06
    /search
    -0.06
    POSITIVE LOGITS
    daş
    0.07
     pohyb
    0.07
    طقة
    0.06
     갖
    0.06
    бо
    0.06
     انسانی
    0.06
     grop
    0.06
    (library
    0.06
    react
    0.06
     πολι
    0.06
    Act Density 0.004%

    No Known Activations