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

    Neuronpedia

    INDEX
    Explanations

    FORMAT(`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Prove
    0.49
    Ii
    0.47
    ьи
    0.44
     stupidity
    0.42
     solicit
    0.42
    ហ
    0.42
     stupid
    0.40
     idiots
    0.40
     outnumbered
    0.39
    ັ
    0.39
    POSITIVE LOGITS
     Bat
    0.43
     Rock
    0.41
     Vo
    0.41
     Beiträge
    0.41
     Fusion
    0.40
     Consume
    0.40
     Cone
    0.40
     Feed
    0.38
     trên
    0.38
     Ola
    0.38
    Act Density 0.000%

    No Known Activations