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

    Neuronpedia

    INDEX
    Explanations

    missing components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ia
    0.80
     embankment
    0.79
     crockery
    0.78
     ক্যামেরা
    0.77
    ід
    0.76
    õe
    0.76
    ज्ञापन
    0.76
    ੇ
    0.75
    ன்ஹீ
    0.75
    adze
    0.75
    POSITIVE LOGITS
     தனி
    0.68
    ۰۰
    0.66
     passing
    0.66
    (!(
    0.66
    それぞれの
    0.65
     শক্ত
    0.64
     ocurren
    0.64
     آنها
    0.64
     επίσης
    0.64
     Alternatively
    0.64
    Act Density 0.001%

    No Known Activations