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

    Neuronpedia

    INDEX
    Explanations

    impeachment proceedings and trials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    しまい
    0.96
    ٹا
    0.93
    یشه
    0.93
    타
    0.90
    <unused653>
    0.86
    𝗱
    0.84
     بین
    0.84
     حتی
    0.84
    larni
    0.84
    𝗮
    0.84
    POSITIVE LOGITS
    2
    1.09
    3
    1.03
    4
    0.98
    ع
    0.98
    6
    0.96
     impeachment
    0.91
    ’
    0.91
     is
    0.90
    }
    0.89
     studies
    0.87
    Act Density 0.000%

    No Known Activations