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

    Neuronpedia

    INDEX
    Explanations

    knowing realizing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GINE
    -0.07
     Economy
    -0.06
    _BOTTOM
    -0.06
     Nadu
    -0.06
    .Student
    -0.06
    _mock
    -0.06
     samt
    -0.06
    nThe
    -0.06
    urement
    -0.06
     Parties
    -0.06
    POSITIVE LOGITS
    езультат
    0.07
    ा:
    0.06
    _row
    0.06
     piercing
    0.06
     Мож
    0.06
     **
    0.06
    уются
    0.06
     декабря
    0.06
    。”↵↵
    0.06
     Notebook
    0.06
    Act Density 0.000%

    No Known Activations