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

    Neuronpedia

    INDEX
    Explanations

    terms related to various factors influencing individual characteristics and group dynamics

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

    list items and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.11
     kasarigan
    -1.03
     surla
    -0.99
    GOTREF
    -0.95
    featureID
    -0.94
    AndEndTag
    -0.93
     Chwiliwch
    -0.92
    <unused41>
    -0.90
    <pad>
    -0.90
    [@BOS@]
    -0.89
    POSITIVE LOGITS
    ↵
    0.34
     sağlar
    0.33
    </b>
    0.33
     &
    0.33
    '
    0.31
    ­
    0.31
    <h1>
    0.28
    就行了
    0.28
    .*;
    0.28
    *
    0.27
    Act Density 2.811%

    No Known Activations