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

    Neuronpedia

    INDEX
    Explanations

    Technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DropColumn
    -0.68
    XmlAccessorType
    -0.57
    DeleteBehavior
    -0.55
    nloa
    -0.52
     '\\;'
    -0.50
    Pry
    -0.50
    Origin
    -0.49
    CloseOperation
    -0.49
    Portale
    -0.47
     origins
    -0.47
    POSITIVE LOGITS
    \{\\
    0.61
    setVerticalGroup
    0.59
    ftagPool
    0.57
     Galbraith
    0.50
    NUMX
    0.49
    Демографія
    0.48
    upné
    0.48
     تانيه
    0.47
    ulipas
    0.47
     Heere
    0.46
    Act Density 0.000%

    No Known Activations