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

    Neuronpedia

    INDEX
    Explanations

    git

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sandbox
    -0.08
     readability
    -0.07
    -mask
    -0.07
     도
    -0.07
    ournal
    -0.06
    .azure
    -0.06
     OID
    -0.06
    /language
    -0.06
    роме
    -0.06
     serviceProvider
    -0.06
    POSITIVE LOGITS
     PHONE
    0.06
    izzie
    0.06
     následující
    0.06
    ís
    0.06
     glaring
    0.06
    	progress
    0.06
     landfill
    0.06
     utiliz
    0.06
     Adult
    0.06
    _Tis
    0.06
    Act Density 0.000%

    No Known Activations