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

    Neuronpedia

    INDEX
    Explanations

    Question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cardinal
    -0.06
    Feature
    -0.06
    Rib
    -0.06
    rito
    -0.06
    flutter
    -0.06
     adrenaline
    -0.06
    빌
    -0.06
     Serif
    -0.06
    .Concat
    -0.06
    Administration
    -0.06
    POSITIVE LOGITS
    ||↵
    0.07
     LAST
    0.07
     Submit
    0.07
     killed
    0.07
     fChain
    0.06
    addPreferredGap
    0.06
     forg
    0.06
    _corr
    0.06
     motel
    0.06
     continues
    0.06
    Act Density 0.007%

    No Known Activations