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

    Neuronpedia

    INDEX
    Explanations

    python code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Blooming
    0.29
    و
    0.29
    eous
    0.29
    кры
    0.28
    ން
    0.27
    та
    0.27
    ل
    0.27
    棻
    0.27
    dehyde
    0.27
    ্যায়
    0.27
    POSITIVE LOGITS
     t
    0.37
     the
    0.30
     it
    0.27
     h
    0.26
     you
    0.26
     d
    0.26
     their
    0.26
     p
    0.26
    0.26
     upto
    0.26
    Act Density 1.262%

    No Known Activations