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

    Neuronpedia

    INDEX
    Explanations

    IT and Marketing contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    噫
    0.45
     enfer
    0.45
     eliminate
    0.44
     llamadas
    0.44
    شک
    0.43
     élim
    0.43
    0.42
     treino
    0.42
     bisogno
    0.42
     asemenea
    0.42
    POSITIVE LOGITS
     ее
    0.45
     RoHS
    0.42
    Door
    0.41
    OS
    0.40
     Соб
    0.40
     मोहित
    0.40
     ਦਿੱ
    0.40
     చక్ర
    0.40
     STE
    0.39
    PPh
    0.39
    Act Density 0.006%

    No Known Activations