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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    qus
    -0.07
    907
    -0.07
     مواط
    -0.06
    =t
    -0.06
    .default
    -0.06
    740
    -0.06
    169
    -0.06
    simulate
    -0.06
     #:
    -0.06
     ##↵
    -0.06
    POSITIVE LOGITS
     liked
    0.07
     canyon
    0.07
     Dixon
    0.07
    َق
    0.06
    Desk
    0.06
    desk
    0.06
     onBlur
    0.06
    _area
    0.06
     anale
    0.06
     dinheiro
    0.06
    Act Density 0.025%

    No Known Activations