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

    Neuronpedia

    INDEX
    Explanations

    sequences of symbols and operators in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    string concatenation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -1.03
     незавершена
    -0.92
     Roskov
    -0.91
     $_"
    -0.89
    iſten
    -0.88
    ➯
    -0.87
    OGND
    -0.85
     imagui
    -0.84
    <unused8>
    -0.84
    <unused74>
    -0.84
    POSITIVE LOGITS
    WriteLiteral
    0.57
     +
    0.56
     is
    0.48
     ==
    0.46
    is
    0.42
    1
    0.42
     =
    0.42
     <<
    0.41
    2
    0.40
    “
    0.40
    Act Density 0.009%

    No Known Activations