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

    Neuronpedia

    INDEX
    Explanations

    program identifiers and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tqdm
    0.47
     mediating
    0.42
     jeweil
    0.41
     mydict
    0.40
     pickled
    0.40
     "".
    0.40
     '$(
    0.38
    matplotlib
    0.38
    sympy
    0.38
    КА
    0.38
    POSITIVE LOGITS
     =
    0.58
     ={
    0.52
     =[
    0.51
    apiUrl
    0.46
    Id
    0.45
    Promise
    0.45
    Width
    0.44
    Promises
    0.42
    eler
    0.41
     URL
    0.41
    Act Density 0.011%

    No Known Activations