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

    Neuronpedia

    INDEX
    Explanations

    chicken powered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कैप
    0.41
     umur
    0.41
     alber
    0.40
     મૂ
    0.39
    ünk
    0.39
    ătă
    0.39
     ছ
    0.39
     Resistance
    0.38
     attain
    0.38
     sensibil
    0.38
    POSITIVE LOGITS
    儀
    0.55
     usb
    0.45
    Также
    0.45
    мети
    0.45
    <0xA1>
    0.44
    oncé
    0.43
     લઇ
    0.43
     grep
    0.42
    ່າ
    0.42
     иначе
    0.41
    Act Density 0.002%

    No Known Activations