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

    Neuronpedia

    INDEX
    Explanations

    additional context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Safety
    -0.07
    (mappedBy
    -0.07
    ighb
    -0.07
     peque
    -0.06
    GU
    -0.06
     pdu
    -0.06
     synd
    -0.06
    contract
    -0.06
     insign
    -0.06
    erç
    -0.06
    POSITIVE LOGITS
     जल
    0.07
     оцен
    0.07
     acknowledged
    0.06
    стор
    0.06
    HasBeen
    0.06
     deb
    0.06
    GetString
    0.06
     permitting
    0.06
    -_
    0.06
     项
    0.06
    Act Density 0.121%

    No Known Activations