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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Data
    0.61
    N
    0.57
    Table
    0.57
    Node
    0.55
    アナ
    0.55
    Toggle
    0.55
    Boolean
    0.54
    Org
    0.54
     trivially
    0.54
    rices
    0.52
    POSITIVE LOGITS
     alegria
    0.93
     incroyable
    0.91
     perjalanan
    0.89
     alegría
    0.88
     usaha
    0.80
     nouă
    0.80
     família
    0.79
     viaggio
    0.79
     całkow
    0.78
     المقبل
    0.78
    Act Density 0.000%

    No Known Activations