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

    Neuronpedia

    INDEX
    Explanations

    letters, creative content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputStream
    0.36
     ({\
    0.36
     _{(
    0.35
    ሉ
    0.34
    ৩৯
    0.33
    อยู่ใน
    0.33
     (\<
    0.33
     Four
    0.33
     glor
    0.33
     queryString
    0.33
    POSITIVE LOGITS
     &
    0.37
    V
    0.35
    Violence
    0.35
    verwaltung
    0.35
     அதனை
    0.32
     V
    0.32
     Vista
    0.32
     вели
    0.31
    バイ
    0.31
     Violence
    0.31
    Act Density 0.016%

    No Known Activations