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

    Neuronpedia

    INDEX
    Explanations

    they make, too complex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    टेगरी
    0.51
    轶
    0.47
    не
    0.46
    สำหรับ
    0.46
     עבור
    0.45
    नैतिक
    0.44
    ichés
    0.43
    వెట్‌
    0.43
    ल्पन
    0.43
    恹
    0.43
    POSITIVE LOGITS
    2
    0.51
     the
    0.42
    .
    0.42
     cette
    0.41
     water
    0.40
    than
    0.40
    </b>
    0.40
    this
    0.40
    ০০
    0.39
    льзя
    0.39
    Act Density 2.677%

    No Known Activations