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

    Neuronpedia

    INDEX
    Explanations

    URLs and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     property
    -0.07
     predictive
    -0.07
    杀
    -0.07
    metadata
    -0.06
     point
    -0.06
    minating
    -0.06
    eneration
    -0.06
    STRUCTIONS
    -0.06
     beneath
    -0.06
     points
    -0.06
    POSITIVE LOGITS
     znam
    0.07
     ủy
    0.07
    0.07
     місті
    0.07
     }↵
    0.06
     ★
    0.06
    .lineWidth
    0.06
     змі
    0.06
     Вы
    0.06
     автом
    0.06
    Act Density 0.064%

    No Known Activations