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

    Neuronpedia

    INDEX
    Explanations

    deny

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ravel
    -0.07
    Database
    -0.07
     gratuit
    -0.07
    ;x
    -0.07
     Whereas
    -0.07
     Directors
    -0.07
    ustral
    -0.07
     Dok
    -0.06
     Sure
    -0.06
     Đối
    -0.06
    POSITIVE LOGITS
     defiance
    0.06
     ActionType
    0.06
     reported
    0.06
    Fed
    0.06
    /st
    0.06
     (--
    0.06
    "sync
    0.06
    arn
    0.06
     borderTop
    0.06
     accessToken
    0.06
    Act Density 0.014%

    No Known Activations