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

    Neuronpedia

    INDEX
    Explanations

    reflected when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vatican
    0.46
     Pagination
    0.43
    It
    0.40
    WebApplication
    0.40
    <?
    0.40
     Moderator
    0.40
     Modulation
    0.39
    자가
    0.39
     Allowed
    0.39
    दू
    0.38
    POSITIVE LOGITS
     gioco
    0.57
    পৃথ
    0.54
     prendere
    0.52
     jogo
    0.50
     almacenamiento
    0.50
    LogProfile
    0.50
     utilizzo
    0.49
     capire
    0.49
    сь
    0.48
     impegno
    0.48
    Act Density 0.004%

    No Known Activations