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

    Neuronpedia

    INDEX
    Explanations

    assignment statements and string definitions in code

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

    HTML or code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    code context markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.75
     houſe
    -0.67
     ſta
    -0.67
    itinéraire
    -0.67
     snippetHide
    -0.66
    Tikang
    -0.65
    ſelves
    -0.64
    WebVitals
    -0.63
     NSCoder
    -0.63
     ſche
    -0.61
    POSITIVE LOGITS
     "
    0.40
     '
    0.38
    <td>
    0.36
     https
    0.35
    ="
    0.35
     http
    0.35
    ='
    0.34
     +
    0.33
    classic
    0.33
     yes
    0.33
    Act Density 0.608%

    No Known Activations