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

    Neuronpedia

    INDEX
    Explanations

    HTML tags that indicate important text formatting, such as bold or strong emphasis

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

    HTML <b> tag

    np_acts-logits-general · gemini-2.0-flash

    appellant's argument

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \\
    -0.90
    <eos>
    -0.87
     b
    -0.81
     qu
    -0.78
     […]
    -0.77
     des
    -0.75
     c
    -0.74
     v
    -0.73
    '];?>
    -0.73
    ）』
    -0.71
    POSITIVE LOGITS
     myſelf
    1.36
     itſelf
    1.34
     Majefty
    1.33
     pleaſure
    1.32
     ſeveral
    1.31
     Houſe
    1.31
    <em>
    1.30
     purpoſe
    1.30
     ſche
    1.29
     houſe
    1.28
    Act Density 0.008%

    No Known Activations