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

    Neuronpedia

    INDEX
    Explanations

    print statements in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Doubles
    0.44
     Double
    0.39
     Bhand
    0.39
    ')";
    0.37
     mogao
    0.37
    ible
    0.36
    Double
    0.36
    🎹
    0.36
     নিঃ
    0.36
     Ella
    0.36
    POSITIVE LOGITS
    assertion
    0.52
     print
    0.47
    print
    0.47
     let
    0.45
     prints
    0.41
     prerequisite
    0.41
    lets
    0.40
    fatal
    0.39
    self
    0.39
    LET
    0.38
    Act Density 0.003%

    No Known Activations