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

    Neuronpedia

    INDEX
    Explanations

    Code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anus
    -0.07
     Nurs
    -0.07
     Samp
    -0.06
    ulsive
    -0.06
    血
    -0.06
     іс
    -0.06
     skill
    -0.06
    POL
    -0.06
    ської
    -0.06
    getVar
    -0.06
    POSITIVE LOGITS
    	manager
    0.07
    Downloader
    0.07
    افق
    0.07
     commentators
    0.06
    .flatten
    0.06
    افه
    0.06
    #endif
    0.06
    (prediction
    0.06
     داشت
    0.06
    消
    0.06
    Act Density 0.000%

    No Known Activations