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

    Neuronpedia

    INDEX
    Explanations

    array declaration or usage patterns in programming code

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

    user function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wilkinson
    -0.47
     McMillan
    -0.47
     Witt
    -0.46
     McManus
    -0.45
     Grossman
    -0.45
     Lieberman
    -0.45
     Wiese
    -0.44
     =
    -0.44
     it
    -0.43
     Wi
    -0.43
    POSITIVE LOGITS
    [],
    1.98
    [])
    1.15
    [];
    1.13
    []);
    1.07
    []):
    1.05
    [])
    1.05
    []){
    1.01
    [];
    0.90
     [],
    0.89
    []>(
    0.85
    Act Density 0.009%

    No Known Activations