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

    Neuronpedia

    INDEX
    Explanations

    break up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    0.94
     out
    0.93
    bing
    0.92
     sánh
    0.90
    й
    0.90
    要知道
    0.87
    ppin
    0.87
     sehen
    0.85
     coup
    0.83
    ée
    0.82
    POSITIVE LOGITS
    dancer
    1.11
    htaking
    1.10
    Hình
    1.06
    hearted
    1.05
     dormancy
    1.04
    dancing
    1.00
    Translation
    1.00
    mold
    0.97
     بینک
    0.95
    ؏
    0.94
    Act Density 0.153%

    No Known Activations