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

    Neuronpedia

    INDEX
    Explanations

    indicators of upcoming content and previews

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

    previews trailers teasers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſy
    -0.40
    Anhalt
    -0.40
     Teal
    -0.38
     sym
    -0.37
     becauſe
    -0.36
    สือ
    -0.36
     theſe
    -0.36
     ſa
    -0.35
    hamshire
    -0.35
     ſche
    -0.35
    POSITIVE LOGITS
     previews
    0.61
     trailer
    0.56
     tráiler
    0.56
     trailers
    0.54
    bukaan
    0.54
     teaser
    0.51
     clips
    0.50
     snippetHide
    0.50
    ThroughAttribute
    0.49
     preview
    0.48
    Act Density 0.012%

    No Known Activations