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

    Neuronpedia

    INDEX
    Explanations

    list separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Although
    0.26
    estado
    0.25
     entirely
    0.25
    ্ের
    0.25
     δεύτε
    0.25
    рыя
    0.24
     मसलन
    0.24
    譬
    0.24
     जोकि
    0.24
    ⤷
    0.24
    POSITIVE LOGITS
     etc
    0.50
    など
    0.49
    ,
    0.46
     ইত্যাদি
    0.44
    ،
    0.44
    ,…
    0.43
    ၊
    0.43
     등
    0.42
    ,),
    0.42
    等等
    0.41
    Act Density 0.627%

    No Known Activations