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

    Neuronpedia

    INDEX
    Explanations

    java utilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wood
    0.44
    ǂ
    0.43
    Bray
    0.39
     তেলেভ
    0.38
    Nub
    0.38
     DMBT
    0.37
     sagittal
    0.37
     elution
    0.37
     schéma
    0.37
     vọng
    0.37
    POSITIVE LOGITS
    Arrays
    0.82
    concurrent
    0.81
    ArrayList
    0.78
    Scanner
    0.72
    stream
    0.70
    HashMap
    0.70
    logging
    0.70
    LinkedList
    0.66
     ArrayList
    0.65
    Iterator
    0.63
    Act Density 0.002%

    No Known Activations