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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.62
    wires
    0.53
     nurt
    0.52
    tei
    0.52
     understandings
    0.52
     imperatives
    0.50
    v
    0.50
    मधून
    0.50
    gyi
    0.50
     delimiters
    0.49
    POSITIVE LOGITS
    9
    0.78
    5
    0.74
    0
    0.69
    7
    0.65
    ۶
    0.64
    6
    0.64
    ۵
    0.59
    ۸
    0.58
    8
    0.57
    ۰
    0.55
    Act Density 0.001%

    No Known Activations