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

    Neuronpedia

    INDEX
    Explanations

    42

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plus
    -0.07
     modèle
    -0.07
    opathy
    -0.06
    _nat
    -0.06
    .way
    -0.06
    по
    -0.06
     burglary
    -0.06
     Seventh
    -0.06
    /tags
    -0.06
    ідно
    -0.06
    POSITIVE LOGITS
    Ан
    0.07
    	Message
    0.07
    рап
    0.06
    usercontent
    0.06
     serviceName
    0.06
    ober
    0.06
     scraped
    0.06
     avenues
    0.06
     lname
    0.06
    ->__
    0.06
    Act Density 0.001%

    No Known Activations