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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting in text

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

    San Diego, confidence intervals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    seits
    -0.31
    1
    -0.27
     and
    -0.26
    x
    -0.25
    2
    -0.24
    ma
    -0.23
    3
    -0.23
    0
    -0.23
    e
    -0.23
    y
    -0.22
    POSITIVE LOGITS
    httphttps
    1.13
     queſta
    0.93
    <unused41>
    0.92
    <unused3>
    0.92
    <unused47>
    0.92
    <unused28>
    0.92
    <unused43>
    0.92
    <unused32>
    0.92
    <unused14>
    0.92
    <unused20>
    0.92
    Act Density 0.187%

    No Known Activations