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

    Neuronpedia

    INDEX
    Explanations

    instances where information is illustrated or highlighted in relation to figures or diagrams

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

    shown in figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.65
    Personendaten
    -0.57
    -0.55
    ScopeManager
    -0.54
     itſelf
    -0.53
    UserScript
    -0.53
     houſe
    -0.51
    frontmatter
    -0.51
    sizeCache
    -0.50
     समीक्षक
    -0.50
    POSITIVE LOGITS
     shown
    1.26
    shown
    1.15
     Shown
    0.94
    Shown
    0.88
     mostrado
    0.74
     showed
    0.69
     gezeigt
    0.68
     shewn
    0.67
     show
    0.67
     displayed
    0.67
    Act Density 0.031%

    No Known Activations