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

    Neuronpedia

    INDEX
    Explanations

    displaying content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rudy
    0.85
    piperidin
    0.83
     RFC
    0.82
     Sebastian
    0.81
     Kevin
    0.80
     ök
    0.80
    keygen
    0.79
    RR
    0.77
     Neumann
    0.77
     Quint
    0.77
    POSITIVE LOGITS
     display
    2.35
    Display
    2.24
     Display
    2.22
    display
    2.13
     displays
    2.07
     Displays
    1.98
     displaying
    1.96
    Displays
    1.90
     displayed
    1.88
     DISPLAY
    1.84
    Act Density 0.336%

    No Known Activations