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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     THIRD
    -0.07
     Scatter
    -0.07
    ])/
    -0.06
    Wi
    -0.06
     Rav
    -0.06
     bedding
    -0.06
     фун
    -0.06
     SAME
    -0.06
    }},↵
    -0.06
     Federal
    -0.06
    POSITIVE LOGITS
     group
    0.07
    increments
    0.06
    ictory
    0.06
     evaluations
    0.06
     imshow
    0.06
    _body
    0.06
     будуть
    0.06
    VRTX
    0.06
    plan
    0.06
    ありがとう
    0.06
    Act Density 0.000%

    No Known Activations