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

    Neuronpedia

    INDEX
    Explanations

    economy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OL
    0.77
    LM
    0.73
     observe
    0.70
    TA
    0.68
     Advantage
    0.66
    LF
    0.66
    Av
    0.66
    LE
    0.65
    ОР
    0.65
     appear
    0.64
    POSITIVE LOGITS
    पिक्सल
    0.77
    ishop
    0.75
     dépenses
    0.73
    selling
    0.72
    ऩे
    0.72
     ग्रेजुएशन
    0.72
     покупки
    0.71
     vendita
    0.71
    PositionY
    0.70
    deletion
    0.70
    Act Density 0.000%

    No Known Activations