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

    Neuronpedia

    INDEX
    Explanations

    currency conversions and historical values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sadie
    0.35
     Phoenix
    0.34
     Nancy
    0.33
    median
    0.33
    anggap
    0.32
    坊
    0.32
    消费
    0.32
    ଣ
    0.32
     Bos
    0.32
     Virgil
    0.32
    POSITIVE LOGITS
     compared
    0.54
     through
    0.47
     compares
    0.46
     vary
    0.46
     throughout
    0.45
     stepwise
    0.45
     expressed
    0.44
     periodically
    0.44
     simulates
    0.44
     varies
    0.43
    Act Density 0.000%

    No Known Activations