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

    Neuronpedia

    INDEX
    Explanations

    all others

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    upload
    -0.07
    Coach
    -0.07
    	client
    -0.07
     Workbook
    -0.07
    .apps
    -0.07
     District
    -0.07
     Sq
    -0.06
     pony
    -0.06
    	save
    -0.06
     suggestion
    -0.06
    POSITIVE LOGITS
     Locate
    0.07
    ailability
    0.06
    ội
    0.06
    volution
    0.06
     contamination
    0.06
     бер
    0.06
    ukkan
    0.06
     mined
    0.05
    链
    0.05
     thác
    0.05
    Act Density 0.005%

    No Known Activations