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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .targets
    -0.06
    imen
    -0.06
    AutoSize
    -0.06
    Copyright
    -0.06
     Implicit
    -0.06
     provisional
    -0.06
     sizing
    -0.06
    _accounts
    -0.06
    eless
    -0.06
    >>)
    -0.06
    POSITIVE LOGITS
     rond
    0.07
     JAXB
    0.07
     Brewers
    0.07
     tới
    0.06
     prac
    0.06
    _Msk
    0.06
    _likelihood
    0.06
    ока
    0.06
     сем
    0.06
     quarterly
    0.06
    Act Density 0.023%

    No Known Activations