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

    Neuronpedia

    INDEX
    Explanations

    Java programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plaster
    0.68
     ergonomic
    0.67
     sociable
    0.65
     endorph
    0.64
     cruelty
    0.64
     mindfulness
    0.63
     comfortable
    0.63
     esports
    0.63
     frontline
    0.63
     renovations
    0.62
    POSITIVE LOGITS
    ArrayList
    0.95
    List
    0.84
    HashMap
    0.84
    HashSet
    0.80
    regex
    0.77
    Arrays
    0.75
     ArrayList
    0.75
    concurrent
    0.69
     Iterator
    0.68
     List
    0.68
    Act Density 0.001%

    No Known Activations