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

    Neuronpedia

    INDEX
    Explanations

    phrases related to close inspection or zooming in on details

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

    close-up detail and examination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.78
     EconPapers
    -0.68
    IUrlHelper
    -0.67
     ujednoznacz
    -0.65
     informée
    -0.65
    httphttps
    -0.64
    Cordialement
    -0.61
    rrggbb
    -0.59
    tvguidetime
    -0.59
    expandindo
    -0.58
    POSITIVE LOGITS
     view
    0.66
     shots
    0.57
    view
    0.54
     examination
    0.45
     detail
    0.44
     shot
    0.42
     revealing
    0.41
    Shots
    0.41
    shot
    0.41
    detail
    0.40
    Act Density 0.032%

    No Known Activations