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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Созд
    -0.07
     הקשר
    -0.07
    أمان
    -0.07
     пре
    -0.07
     ذو
    -0.06
    _TRI
    -0.06
    ﯯ
    -0.06
     Bölge
    -0.06
    ROC
    -0.06
     Lies
    -0.06
    POSITIVE LOGITS
    -water
    0.07
     rendered
    0.07
    (ArrayList
    0.07
     gamer
    0.07
    高
    0.07
    ⾼
    0.07
     повышен
    0.07
    عنا
    0.07
     volum
    0.07
     read
    0.07
    Act Density 0.004%

    No Known Activations