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

    Neuronpedia

    INDEX
    Explanations

    part

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۓ
    -0.07
     arrayOf
    -0.07
     ма
    -0.07
     consequences
    -0.07
     Mum
    -0.07
    Portrait
    -0.06
    权力
    -0.06
    	sp
    -0.06
    QRS
    -0.06
     appropriation
    -0.06
    POSITIVE LOGITS
    :{}
    0.07
     outliers
    0.07
     ج
    0.07
    _Last
    0.07
    主人
    0.06
    롯
    0.06
    .allow
    0.06
     pleasantly
    0.06
     ejemplo
    0.06
    덩
    0.06
    Act Density 0.016%

    No Known Activations