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

    Neuronpedia

    INDEX
    Explanations

    start of text / ingredients / sleepy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bikes
    0.89
     brownies
    0.88
    em
    0.82
    量を
    0.82
     Kanpur
    0.81
     bananas
    0.80
     Chhattisgarh
    0.80
     prion
    0.80
     vacations
    0.79
    on
    0.79
    POSITIVE LOGITS
    <0x80>
    0.94
    ت
    0.93
    ุท
    0.79
    ️⃣
    0.73
    렉
    0.71
    HOUT
    0.70
    ト
    0.69
    יה
    0.69
    اس
    0.68
     जहाज़
    0.68
    Act Density 0.000%

    No Known Activations