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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    via
    -0.52
    at
    -0.47
    é
    -0.45
     via
    -0.45
    live
    -0.45
    no
    -0.45
    j
    -0.45
    k
    -0.45
    .
    -0.44
     <
    -0.42
    POSITIVE LOGITS
     فريبيس
    1.39
     الحره
    0.90
     myſelf
    0.89
     Monfieur
    0.85
     itſelf
    0.85
     Majefty
    0.84
     himſelf
    0.81
     समीक्षाओं
    0.81
    expandindo
    0.79
     referenties
    0.78
    Act Density 0.016%

    No Known Activations