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

    Neuronpedia

    INDEX
    Explanations

    continuous availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เบ
    0.66
    ├──
    0.64
    棚
    0.62
     Medicaid
    0.61
     Alia
    0.60
    bra
    0.59
     ఫో
    0.59
     Fal
    0.59
    మార్
    0.58
     пробе
    0.58
    POSITIVE LOGITS
     continuous
    1.14
     continuously
    1.13
     constantly
    1.10
     constant
    1.07
     Continuous
    1.03
    Continuous
    1.03
     Constant
    1.00
     unrelenting
    0.99
     continuamente
    0.97
     continual
    0.97
    Act Density 0.145%

    No Known Activations