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

    Neuronpedia

    INDEX
    Explanations

    c++ code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Py
    0.54
    Python
    0.52
    Py
    0.51
     Python
    0.48
     Pythagorean
    0.48
     python
    0.46
     pyrid
    0.46
    Sc
    0.43
     pir
    0.42
     pym
    0.42
    POSITIVE LOGITS
    cpp
    0.58
     cpp
    0.56
    CPP
    0.46
     CPP
    0.43
    macosx
    0.40
     баш
    0.37
     veille
    0.37
    atschapp
    0.37
     ඉද
    0.36
    ("//
    0.36
    Act Density 0.014%

    No Known Activations