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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “But
    -0.07
    りの
    -0.06
    Pal
    -0.06
     avenue
    -0.06
    okie
    -0.06
     outnumber
    -0.06
    /material
    -0.06
     lagi
    -0.06
     Вики
    -0.06
    ุตบอล
    -0.06
    POSITIVE LOGITS
    _runs
    0.07
     yacht
    0.06
     itch
    0.06
    _managed
    0.06
    integr
    0.06
     ord
    0.06
     busy
    0.06
    _install
    0.06
     tails
    0.06
     приклад
    0.06
    Act Density 0.074%

    No Known Activations