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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alloween
    -0.07
    ".$
    -0.07
     toddlers
    -0.07
    ころ
    -0.07
    earable
    -0.06
     topic
    -0.06
     Rural
    -0.06
    시
    -0.06
    acin
    -0.06
    .sponge
    -0.06
    POSITIVE LOGITS
    lead
    0.06
    Nhap
    0.06
     Scottish
    0.06
    加入
    0.06
     asserting
    0.06
     allure
    0.06
     crunchy
    0.06
     Amend
    0.06
     of
    0.06
     aide
    0.06
    Act Density 0.008%

    No Known Activations