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

    Neuronpedia

    INDEX
    Explanations

    financial rate variable 'r'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نات
    0.32
     indefin
    0.31
    emás
    0.31
    🕓
    0.30
    Mitchell
    0.29
    Netflix
    0.29
    Roots
    0.29
    ፈጥ
    0.29
    Logs
    0.28
    母亲
    0.28
    POSITIVE LOGITS
     r
    0.55
     R
    0.48
    )^
    0.46
    dfrac
    0.42
    ]^
    0.41
    利率
    0.39
    ))^
    0.38
    r
    0.38
    R
    0.37
     Rates
    0.35
    Act Density 0.000%

    No Known Activations