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

    Neuronpedia

    INDEX
    Explanations

    Ti Rosa One else die 4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     продук
    0.62
     ت
    0.54
    nią
    0.53
     س
    0.48
     ау
    0.47
     ع
    0.47
     продукции
    0.47
    dington
    0.47
     स
    0.47
     आधार
    0.47
    POSITIVE LOGITS
    ير
    0.56
     Dear
    0.53
    V
    0.52
    2
    0.52
    istische
    0.51
    g
    0.51
     simply
    0.50
    Dear
    0.50
    itoare
    0.50
    Yeni
    0.50
    Act Density 0.000%

    No Known Activations