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

    Neuronpedia

    INDEX
    Explanations

    consumption and choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    2.13
    ان
    1.78
    ной
    1.71
    न
    1.59
    ку
    1.55
    すみ
    1.54
    мо
    1.51
    не
    1.49
    ੂ
    1.49
    وس
    1.48
    POSITIVE LOGITS
     وعلى
    1.80
     niên
    1.59
    utta
    1.48
    ura
    1.47
     đích
    1.45
     Elevations
    1.43
     Consumption
    1.40
     Conversations
    1.40
    та
    1.39
    idade
    1.38
    Act Density 0.011%

    No Known Activations