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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ellers
    -0.07
    loadModel
    -0.06
     сайті
    -0.06
    gment
    -0.06
     Invest
    -0.06
    deck
    -0.06
    ORIZATION
    -0.06
    .hu
    -0.06
     gu
    -0.06
    �m
    -0.06
    POSITIVE LOGITS
     repairs
    0.07
    ольку
    0.07
     opr
    0.06
    ैट
    0.06
     ISIL
    0.06
    +=
    0.06
    국
    0.06
    allback
    0.06
     Stephanie
    0.06
     '')↵
    0.06
    Act Density 0.226%

    No Known Activations