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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.94
    ,
    0.91
     ¾
    0.89
     in
    0.88
    0.83
     of
    0.81
     with
    0.81
    م
    0.81
     hallmarks
    0.81
     das
    0.80
    POSITIVE LOGITS
    0
    1.14
    Ге
    1.08
    Inte
    1.04
    issante
    1.03
    это
    1.02
    Чи
    1.00
    Ч
    0.97
    <unused670>
    0.97
    ीडियो
    0.96
    Jumlah
    0.96
    Act Density 0.174%

    No Known Activations