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

    Neuronpedia

    INDEX
    Explanations

    patterns related to code structure and comments

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

    code documentation or mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.05
    ſchaft
    -1.01
    niſſe
    -1.00
    WriteTagHelper
    -0.98
    <unused14>
    -0.97
    <unused68>
    -0.97
    <unused74>
    -0.97
    <unused52>
    -0.97
    <unused79>
    -0.97
    [@BOS@]
    -0.96
    POSITIVE LOGITS
    .
    0.42
    </td>
    0.35
    2
    0.32
    @
    0.31
    3
    0.31
     =
    0.30
    1
    0.29
    5
    0.29
    MathML
    0.29
     .
    0.28
    Act Density 0.006%

    No Known Activations