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

    Neuronpedia

    INDEX
    Explanations

    URLs and web links

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

    website urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſte
    -1.02
    <unused79>
    -1.02
    <unused14>
    -1.02
    [@BOS@]
    -1.01
    <unused41>
    -1.01
    <unused16>
    -1.01
    <unused28>
    -1.01
    <unused23>
    -1.01
    <unused3>
    -1.01
    <unused8>
    -1.01
    POSITIVE LOGITS
    ://
    0.88
     website
    0.57
    www
    0.53
     www
    0.51
    website
    0.43
     the
    0.42
    The
    0.41
    .
    0.41
     Website
    0.39
    @
    0.36
    Act Density 0.010%

    No Known Activations