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

    Neuronpedia

    INDEX
    Explanations

    numbers and digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    스를
    0.53
     الاستفهام
    0.51
    ❦
    0.50
    🎿
    0.49
     них
    0.48
     тях
    0.47
     видели
    0.47
    途径
    0.47
    掇
    0.47
    ла
    0.46
    POSITIVE LOGITS
    1
    0.55
    9
    0.54
    8
    0.54
     I
    0.51
    3
    0.51
    7
    0.50
    0
    0.48
    4
    0.47
     eighteen
    0.46
     twists
    0.44
    Act Density 0.002%

    No Known Activations