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

    Neuronpedia

    INDEX
    Explanations

    row in tables and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ר
    1.38
     or
    1.36
     on
    1.24
    >
    1.16
     to
    1.14
    י
    1.14
    ll
    1.13
    д
    1.09
    ك
    1.09
    ↵
    1.09
    POSITIVE LOGITS
    ер
    1.06
    एस
    1.02
     отмети
    0.99
    ort
    0.91
    स्पति
    0.91
    N
    0.88
     взя
    0.87
     बरकरार
    0.86
     цело
    0.86
     возмо
    0.85
    Act Density 0.023%

    No Known Activations