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

    Neuronpedia

    INDEX
    Explanations

    scale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wyoming
    -0.08
    amble
    -0.07
    ᠭ
    -0.07
     jugg
    -0.07
    _Server
    -0.07
    ﾟ
    -0.07
    转型升级
    -0.07
    addTo
    -0.07
    oram
    -0.07
    绝大部分
    -0.07
    POSITIVE LOGITS
     characteristic
    0.07
    那位
    0.07
     Clippers
    0.07
    ｌ
    0.07
    levator
    0.07
    招聘
    0.06
     estudiantes
    0.06
    _notification
    0.06
    รายงาน
    0.06
    /Observable
    0.06
    Act Density 0.003%

    No Known Activations