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

    Neuronpedia

    INDEX
    Explanations

    collections and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Accidents
    0.75
    ক্ষেপ
    0.72
     Gottlieb
    0.66
     Cain
    0.65
    AfterTax
    0.65
     ukon
    0.63
     বালা
    0.63
    নিষ্ঠ
    0.62
    nin
    0.61
     silks
    0.60
    POSITIVE LOGITS
    Map
    2.04
     Map
    2.01
    HashMap
    1.93
     HashSet
    1.85
    HashSet
    1.85
     HashMap
    1.70
    Hash
    1.61
     Hash
    1.60
     Dictionary
    1.56
    Dictionary
    1.55
    Act Density 0.195%

    No Known Activations