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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tribute
    -0.06
    <F
    -0.06
    ension
    -0.06
    ORN
    -0.06
     street
    -0.06
     shipped
    -0.06
     behalf
    -0.06
     CHK
    -0.06
     at
    -0.06
     orders
    -0.06
    POSITIVE LOGITS
    SizePolicy
    0.07
     polarization
    0.07
     электр
    0.07
    0.07
    0.06
    useState
    0.06
    ær
    0.06
    (man
    0.06
     Structure
    0.06
    paralleled
    0.06
    Act Density 0.013%

    No Known Activations