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

    Neuronpedia

    INDEX
    Explanations

    distances and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.70
     By
    0.65
     Scholarships
    0.65
     by
    0.64
    ों
    0.63
     Studies
    0.61
    ים
    0.60
     This
    0.59
     Astronomy
    0.59
     =
    0.59
    POSITIVE LOGITS
    р
    0.91
    ي
    0.81
    o
    0.80
    ла
    0.79
    น
    0.77
    ли
    0.76
     foothold
    0.71
    ра
    0.69
     malicious
    0.69
    ak
    0.67
    Act Density 0.127%

    No Known Activations