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

    Neuronpedia

    INDEX
    Explanations

    locations and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    0.96
    le
    0.77
    y
    0.77
    od
    0.74
    ق
    0.74
    erson
    0.73
    t
    0.73
    por
    0.71
    c
    0.70
    alo
    0.69
    POSITIVE LOGITS
    ：“
    0.77
     monetize
    0.74
     Пусть
    0.72
     bluff
    0.70
     implicate
    0.69
    磧
    0.68
    ্রান্ত
    0.68
     टूट
    0.68
     zwią
    0.68
     Macros
    0.67
    Act Density 0.000%

    No Known Activations