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

    Neuronpedia

    INDEX
    Explanations

    calibration status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сту
    0.44
    ↵
    0.42
    Celebr
    0.42
    ानी
    0.41
    оти
    0.41
     stormed
    0.41
     gingerbread
    0.41
     Shea
    0.40
     நடைபெற்றது
    0.40
    //
    0.39
    POSITIVE LOGITS
     AcOH
    0.55
     Become
    0.49
     collim
    0.48
     essentiellement
    0.46
    ycop
    0.46
     OFDM
    0.45
     epistem
    0.45
     sớm
    0.45
     Among
    0.44
     Hamming
    0.44
    Act Density 0.002%

    No Known Activations