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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mobile
    -0.07
    뉴
    -0.07
    илися
    -0.07
    .orders
    -0.06
    培训
    -0.06
     prisoners
    -0.06
     adventurers
    -0.06
    анню
    -0.06
    userId
    -0.06
    mens
    -0.06
    POSITIVE LOGITS
    UNET
    0.07
    盟
    0.06
     acknowledging
    0.06
    ución
    0.06
    sol
    0.06
    CED
    0.06
     Ec
    0.06
     redefine
    0.06
     champion
    0.06
     اد
    0.06
    Act Density 0.006%

    No Known Activations