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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BRANCH
    -0.07
    ierte
    -0.07
     kullan
    -0.06
     //{
    -0.06
     astronomers
    -0.06
     zcela
    -0.06
    _histogram
    -0.06
     Meredith
    -0.06
     framework
    -0.06
    _iterations
    -0.06
    POSITIVE LOGITS
     lively
    0.07
    [])
    0.06
    tensorflow
    0.06
    ime
    0.06
    ↵      ↵
    0.06
    ioneer
    0.06
     mariage
    0.06
    093
    0.06
     Dialog
    0.06
    咨
    0.06
    Act Density 0.005%

    No Known Activations