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

    Neuronpedia

    INDEX
    Explanations

    days followed by closing quote punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蓦
    0.61
    लिब्र
    0.60
     “
    0.60
     træ
    0.59
    ugging
    0.58
    +:
    0.58
    ächer
    0.58
    ↵
    0.57
     কাছ
    0.57
    నో
    0.57
    POSITIVE LOGITS
    .")
    3.16
    。」
    3.15
    ."
    3.13
    。”
    3.05
    .”
    3.05
    .”)
    3.00
    ."]
    2.96
    .",
    2.80
    ?"
    2.75
    !"
    2.71
    Act Density 1.329%

    No Known Activations