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

    Neuronpedia

    INDEX
    Explanations

    visualisation tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我知道
    0.43
     मेरा
    0.43
     மயில
    0.39
     conservation
    0.39
    უს
    0.39
     знал
    0.39
     Marcello
    0.38
     был
    0.38
     теория
    0.38
     ядер
    0.38
    POSITIVE LOGITS
     elsewhere
    0.44
    騎
    0.42
     coarse
    0.41
     undertake
    0.40
     seves
    0.40
     Calculate
    0.40
     trivial
    0.39
    NUMBER
    0.39
     partake
    0.38
     exquisite
    0.38
    Act Density 0.020%

    No Known Activations