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

    Neuronpedia

    INDEX
    Explanations

    Probability calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fprintf
    -0.07
    Opacity
    -0.07
     gloss
    -0.07
    ugins
    -0.07
    cr
    -0.07
     penetrating
    -0.06
    anmar
    -0.06
    妻
    -0.06
    Booking
    -0.06
    _formats
    -0.06
    POSITIVE LOGITS
    чої
    0.07
    /preferences
    0.06
    (all
    0.06
    ху
    0.06
     времени
    0.06
    �
    0.06
     Борис
    0.06
     delaying
    0.06
    /",↵
    0.06
    기의
    0.06
    Act Density 0.004%

    No Known Activations