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

    Neuronpedia

    INDEX
    Explanations

    programming language keywords and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     williams
    0.51
     pituitary
    0.51
     jdbc
    0.50
     tannin
    0.50
     anthocyan
    0.48
     pyrite
    0.48
     tienden
    0.48
     WILLIAM
    0.47
     kože
    0.47
     tyrosine
    0.47
    POSITIVE LOGITS
     IEnumerable
    1.21
    IEnumerable
    1.19
    Dictionary
    1.02
    bool
    1.01
    foreach
    0.97
     HashSet
    0.97
     foreach
    0.93
     bool
    0.93
     Dictionary
    0.93
    HashSet
    0.93
    Act Density 0.052%

    No Known Activations