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

    Neuronpedia

    INDEX
    Explanations

    function or method calls related to logging or printing output in code

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

    programming output and user prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.73
    Демографія
    -0.70
    :✨
    -0.70
    protoimpl
    -0.68
    -0.68
    bufio
    -0.66
    WebElementEntity
    -0.66
     мәкал
    -0.65
     ब्रेकडाउन
    -0.65
    iſchen
    -0.64
    POSITIVE LOGITS
     also
    0.47
     additional
    0.42
     further
    0.39
     "
    0.39
     square
    0.38
     ta
    0.36
    也
    0.33
     here
    0.32
    also
    0.32
    MarshalTo
    0.32
    Act Density 0.009%

    No Known Activations