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

    Neuronpedia

    INDEX
    Explanations

    javascript object data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     швид
    0.43
     JSONArray
    0.42
    JSONArray
    0.42
     sitzt
    0.42
    SetStr
    0.42
     blat
    0.41
    NSMutableArray
    0.41
     Tubular
    0.40
     ہوجائے
    0.39
    inander
    0.39
    POSITIVE LOGITS
    ({...
    0.89
     {...
    0.85
     objeto
    0.84
     object
    0.82
    ={
    0.80
     //{
    0.79
     ({
    0.79
     ={
    0.76
    //{
    0.76
     ऑब्जेक्ट
    0.75
    Act Density 0.025%

    No Known Activations