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

    Neuronpedia

    INDEX
    Explanations

    , до , be , the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    વ
    0.96
     serta
    0.83
    م
    0.81
    л
    0.81
     hashlib
    0.77
    ય
    0.76
    м
    0.75
    以及
    0.75
    ية
    0.74
    そして
    0.74
    POSITIVE LOGITS
    od
    1.01
    ot
    0.96
     tega
    0.92
    on
    0.88
    k
    0.88
    Deux
    0.85
    are
    0.85
    دة
    0.85
    id
    0.83
     corretamente
    0.76
    Act Density 0.352%

    No Known Activations