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
     CALLBACK
    -0.07
    .json
    -0.07
    	map
    -0.07
    γκ
    -0.07
    ().'
    -0.07
     sacked
    -0.07
    (hist
    -0.06
     costly
    -0.06
     species
    -0.06
     abolished
    -0.06
    POSITIVE LOGITS
     回
    0.06
     mẽ
    0.06
    oire
    0.06
     testimonials
    0.06
    ladığ
    0.06
    using
    0.06
    ुई
    0.06
    /display
    0.06
     �
    0.06
     telemetry
    0.06
    Act Density 0.057%

    No Known Activations