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

    Neuronpedia

    INDEX
    Explanations

    delays and slowness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     knew
    -0.07
    成熟的
    -0.07
    ords
    -0.07
     Railroad
    -0.07
     Planning
    -0.07
    |wx
    -0.07
     himself
    -0.06
    劳动者
    -0.06
    _Title
    -0.06
     אזרחי
    -0.06
    POSITIVE LOGITS
    แพทย
    0.08
    早晚
    0.07
    🏛
    0.07
    ▓
    0.07
     Abd
    0.07
    散热
    0.07
    Ⓖ
    0.07
    totals
    0.07
    闪
    0.07
     Aleks
    0.07
    Act Density 0.031%

    No Known Activations