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

    Neuronpedia

    INDEX
    Explanations

    technical and procedural content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    島
    0.38
     Aralık
    0.38
     없이
    0.37
     শতাব্দীর
    0.36
    ธุรก
    0.36
     المثلثيه
    0.35
    мато
    0.35
    انيه
    0.35
     ヘア
    0.35
    展示
    0.35
    POSITIVE LOGITS
     ballast
    0.33
     Liquor
    0.33
     Kev
    0.33
     حاضر
    0.31
    NUMBER
    0.29
    abs
    0.29
    NOR
    0.29
    دم
    0.29
     bast
    0.29
    purpose
    0.29
    Act Density 0.000%

    No Known Activations