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

    Neuronpedia

    INDEX
    Explanations

    patent numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    about
    -0.07
    overrides
    -0.06
    nte
    -0.06
    pps
    -0.06
    _xt
    -0.06
    ?";↵
    -0.06
    observ
    -0.06
    .s
    -0.06
    IN
    -0.06
    ABOUT
    -0.06
    POSITIVE LOGITS
    約
    0.07
    rebbe
    0.07
    볼
    0.06
     grund
    0.06
     mücadele
    0.06
     thankfully
    0.06
     potentially
    0.06
     pci
    0.06
     conhec
    0.06
     wym
    0.06
    Act Density 0.011%

    No Known Activations