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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sacrifices
    -0.07
    end
    -0.06
     trick
    -0.06
     fathers
    -0.06
    .sleep
    -0.06
    	test
    -0.06
     fellows
    -0.06
     mamm
    -0.06
     doctor
    -0.06
     Close
    -0.06
    POSITIVE LOGITS
    /ac
    0.07
    elloworld
    0.07
     replied
    0.07
    ujte
    0.07
    useRalativeImagePath
    0.06
     Lanc
    0.06
    uname
    0.06
     createdBy
    0.06
    bounds
    0.06
    /gallery
    0.06
    Act Density 0.030%

    No Known Activations