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

    Neuronpedia

    INDEX
    Explanations

    email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    boost
    -0.07
    ⿃
    -0.07
    .djangoproject
    -0.07
    yız
    -0.07
    创新驱动
    -0.06
     explores
    -0.06
    _KP
    -0.06
    edido
    -0.06
     bottoms
    -0.06
     YYSTACK
    -0.06
    POSITIVE LOGITS
    arrivée
    0.08
     limestone
    0.07
     ACS
    0.07
     workstation
    0.07
    erne
    0.07
     lantern
    0.07
    -paced
    0.07
     helmet
    0.07
    ︱
    0.07
    Running
    0.07
    Act Density 0.013%

    No Known Activations