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

    Neuronpedia

    INDEX
    Explanations

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Released
    0.45
     acquitted
    0.44
    RELEASE
    0.44
     RELEASE
    0.44
     release
    0.42
    释放
    0.42
    Release
    0.40
    Released
    0.40
     releasing
    0.40
     acquittal
    0.38
    POSITIVE LOGITS
     প্রেক্ষিতে
    0.46
     preocup
    0.40
     ব্যাপার
    0.37
    コク
    0.36
     dirigentes
    0.35
    孬
    0.35
     হঠাৎ
    0.35
     preocupa
    0.35
     bestuur
    0.35
     گفته
    0.34
    Act Density 0.003%

    No Known Activations