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

    Neuronpedia

    INDEX
    Explanations

    numbers and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     هناخد
    0.30
    郴
    0.27
    蓴
    0.26
    钀
    0.26
    फर्म
    0.26
     सोच
    0.25
    پاکستان
    0.25
    㣙
    0.25
    द्दी
    0.25
     उपलब्धता
    0.25
    POSITIVE LOGITS
    0
    0.54
    5
    0.52
    9
    0.51
    3
    0.50
    8
    0.49
    6
    0.47
    4
    0.46
    2
    0.45
    7
    0.45
    1
    0.42
    Act Density 0.360%

    No Known Activations