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

    Neuronpedia

    INDEX
    Explanations

    encountering things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ена
    0.98
    ре
    0.83
     و
    0.77
    یم
    0.76
    东西
    0.72
     asegurar
    0.72
    рены
    0.71
    랗
    0.70
    芢
    0.70
    。”
    0.69
    POSITIVE LOGITS
     encounter
    1.00
     encountered
    0.93
    6
    0.90
    ז
    0.88
    7
    0.86
    8
    0.84
    5
    0.84
     encounters
    0.83
    encountered
    0.80
    w
    0.79
    Act Density 0.065%

    No Known Activations