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

    Neuronpedia

    INDEX
    Explanations

    initiating clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extraordinaire
    0.51
     esclusivamente
    0.51
     gerçekleş
    0.46
     classically
    0.46
    '
    0.46
    Nella
    0.46
    IS
    0.46
     dirinya
    0.46
    ждый
    0.45
    s
    0.45
    POSITIVE LOGITS
    ون
    0.64
    ام
    0.55
    ان
    0.55
    t
    0.51
    ри
    0.50
    िन
    0.48
    ab
    0.47
    اد
    0.47
    ik
    0.46
    ری
    0.46
    Act Density 0.673%

    No Known Activations