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

    Neuronpedia

    INDEX
    Explanations

    concepts related to what is important and meaningful in people's lives

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

    what really matters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    />";
    -0.41
     }}</
    -0.41
    mergeFrom
    -0.38
    $}}
    -0.38
    LayoutStyle
    -0.37
    后面
    -0.33
     melted
    -0.33
     cartilage
    -0.33
     Desh
    -0.32
    $),
    -0.32
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.68
     الرياضيه
    0.57
    verwijspagina
    0.52
    0.52
     autorytatywna
    0.52
    ThroughAttribute
    0.52
    httphttps
    0.51
     незавершена
    0.50
    ыгана
    0.49
    agt
    0.45
    Act Density 0.135%

    No Known Activations