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

    Neuronpedia

    INDEX
    Explanations

    compound interest and returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jumping
    0.48
     jogging
    0.43
     threading
    0.43
     self
    0.42
     iee
    0.42
     olen
    0.41
     steering
    0.41
     threaded
    0.41
     jargon
    0.41
     sii
    0.41
    POSITIVE LOGITS
    日
    0.46
    Lux
    0.43
    ⿶
    0.43
    咖
    0.43
    0.43
    ข
    0.41
    ฝ
    0.41
    ༸
    0.41
     všetky
    0.40
    ษ
    0.40
    Act Density 0.004%

    No Known Activations