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

    Neuronpedia

    INDEX
    Explanations

    for example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.46
    +.
    0.45
    3
    0.42
     }.
    0.38
    -(
    0.37
     повністю
    0.36
     approx
    0.36
    ().
    0.36
    *.
    0.36
     அனைத்து
    0.35
    POSITIVE LOGITS
    например
    0.56
     например
    0.49
    অর্থাৎ
    0.49
     которым
    0.48
     például
    0.47
     как
    0.47
     mesela
    0.46
    例えば
    0.46
    как
    0.45
    собенно
    0.45
    Act Density 0.159%

    No Known Activations