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

    Neuronpedia

    INDEX
    Explanations

    taking turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.06
     l
    0.80
     u
    0.79
    т
    0.77
     t
    0.71
     d
    0.69
    ت
    0.69
     wafer
    0.68
     restaurante
    0.64
    j
    0.64
    POSITIVE LOGITS
     उपयोग
    0.64
    ንሽ
    0.59
    ப்பிக்க
    0.57
    يبة
    0.54
    ynaptic
    0.52
    henius
    0.52
    δη
    0.51
    նել
    0.51
    clonal
    0.51
    withstanding
    0.50
    Act Density 0.007%

    No Known Activations