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

    Neuronpedia

    INDEX
    Explanations

    specific technical nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    1.24
    heten
    1.02
     уж
    1.01
     말미암
    0.99
    いは
    0.99
     Bumi
    0.99
     unimaginable
    0.98
     incomparable
    0.98
     거의
    0.97
     বিস্ম
    0.96
    POSITIVE LOGITS
    5
    1.03
    0
    1.02
    数据集
    0.98
    שים
    0.98
    ల
    0.97
    Ре
    0.95
     notifies
    0.95
     длиной
    0.93
    वायु
    0.92
    נ
    0.91
    Act Density 0.544%

    No Known Activations