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

    Neuronpedia

    INDEX
    Explanations

    Scientific research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boosted
    -0.07
    elfare
    -0.06
     brisk
    -0.06
    หว
    -0.06
    Notify
    -0.06
     시장
    -0.06
    embourg
    -0.06
    SSF
    -0.06
    ÷
    -0.06
     Mr
    -0.06
    POSITIVE LOGITS
    ानव
    0.07
    헌
    0.07
     желуд
    0.07
     Lily
    0.06
    Disclosure
    0.06
    荷
    0.06
     начала
    0.06
     mediated
    0.06
    �
    0.06
    InnerText
    0.06
    Act Density 0.015%

    No Known Activations