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

    Neuronpedia

    INDEX
    Explanations

    programming language data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sticks
    0.88
     бал
    0.80
     stick
    0.76
     agents
    0.76
     barons
    0.72
    islation
    0.71
     princes
    0.70
     knights
    0.70
     Stick
    0.69
     agentes
    0.68
    POSITIVE LOGITS
    HashMap
    0.88
    HashSet
    0.82
     HashSet
    0.78
    ArrayList
    0.77
    NSMutable
    0.76
    mutable
    0.72
     NSMutable
    0.71
    Linked
    0.69
     görd
    0.66
     মহাম
    0.66
    Act Density 0.089%

    No Known Activations