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

    Neuronpedia

    INDEX
    Explanations

    Theoretical physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Q
    -0.07
     Wend
    -0.06
     Alexa
    -0.06
    Disable
    -0.06
    	Check
    -0.06
     UserData
    -0.06
     applaud
    -0.06
    _align
    -0.06
     genitals
    -0.06
     ub
    -0.06
    POSITIVE LOGITS
     البحر
    0.07
     Nico
    0.07
     Goose
    0.07
     CARD
    0.07
     εκεί
    0.07
    .include
    0.06
    /video
    0.06
    .authenticate
    0.06
    ево
    0.06
     GPI
    0.06
    Act Density 0.020%

    No Known Activations