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

    Neuronpedia

    INDEX
    Explanations

    data validation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iku
    -0.07
    hait
    -0.06
     Tests
    -0.06
    Sheet
    -0.06
    ousand
    -0.06
    010
    -0.06
     thesis
    -0.06
    olve
    -0.06
    egr
    -0.06
    gradable
    -0.06
    POSITIVE LOGITS
     snork
    0.07
    -sample
    0.06
     intest
    0.06
     ст
    0.06
    lator
    0.06
     повтор
    0.06
    battery
    0.06
     Ext
    0.06
     Printer
    0.06
     mappings
    0.06
    Act Density 0.064%

    No Known Activations