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

    Neuronpedia

    INDEX
    Explanations

    complete

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gaussian
    -0.07
     figure
    -0.07
    ，说
    -0.07
     traff
    -0.07
     exponent
    -0.07
     strstr
    -0.07
     fund
    -0.06
    aussian
    -0.06
     imageName
    -0.06
     estr
    -0.06
    POSITIVE LOGITS
     completed
    0.10
     completing
    0.09
     Complete
    0.08
    COMPLETE
    0.08
     completion
    0.08
    Complete
    0.08
     complete
    0.08
     depleted
    0.08
    Completed
    0.08
    completed
    0.07
    Act Density 0.050%

    No Known Activations