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

    Neuronpedia

    INDEX
    Explanations

    COVID-19

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eers
    1.14
    dogs
    1.13
    arrows
    1.12
    eat
    1.12
    e
    1.11
    اا
    1.09
    eaa
    1.07
     buna
    1.05
    هه
    1.04
    cakes
    1.03
    POSITIVE LOGITS
    ृत्व
    1.21
    atrical
    1.07
     excruciating
    1.03
     simmering
    1.03
    基づ
    1.02
    <0x80>
    1.02
     cherished
    1.01
     grieving
    0.99
     minted
    0.97
    iminary
    0.97
    Act Density 0.001%

    No Known Activations