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

    Neuronpedia

    INDEX
    Explanations

    HEL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ์แ
    -0.07
     法
    -0.07
    ських
    -0.07
    emente
    -0.07
    :_
    -0.07
    ograd
    -0.07
    テル
    -0.06
    іка
    -0.06
    多
    -0.06
     Flag
    -0.06
    POSITIVE LOGITS
     article
    0.07
     sx
    0.06
     fatalError
    0.06
     Highlands
    0.06
     realizing
    0.06
     Janet
    0.06
     clips
    0.06
     createAction
    0.06
     dlg
    0.06
     Prices
    0.05
    Act Density 0.001%

    No Known Activations