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

    Neuronpedia

    INDEX
    Explanations

    elements that suggest structure or organization, such as headers, bullet points, and function definitions

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

    Mathematical or code notation

    np_acts-logits-general · gemini-2.0-flash

    beginning of introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -1.15
    msgTypes
    -0.97
     ligiloj
    -0.94
     queſta
    -0.93
     surla
    -0.90
     ujednoznacz
    -0.89
    帖最后由
    -0.88
    <unused41>
    -0.86
    ſicht
    -0.86
    <unused8>
    -0.86
    POSITIVE LOGITS
    s
    0.45
    ↵↵
    0.45
    <eos>
    0.40
    ="
    0.34
    1
    0.33
    [toxicity=0]
    0.32
    2
    0.32
    <strong>
    0.31
     is
    0.31
    ’
    0.31
    Act Density 0.025%

    No Known Activations