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

    Neuronpedia

    INDEX
    Explanations

    words related to titles and headings in texts

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

    Tokens preceding "Screen" or a "title"

    np_acts-logits-general · gemini-2.0-flash

    title text after colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.58
    onshire
    -0.55
    isinstance
    -0.49
    茅
    -0.48
    WriteBarrier
    -0.48
     termin
    -0.48
     Gad
    -0.47
    inetti
    -0.47
    ()")
    -0.47
    MergeFrom
    -0.46
    POSITIVE LOGITS
    holders
    0.67
    AndEndTag
    0.66
    bar
    0.65
    RetentionPolicy
    0.58
    page
    0.58
     Chwiliwch
    0.57
    GEBURTS
    0.56
     Sponsor
    0.56
     autorytatywna
    0.56
    OGND
    0.56
    Act Density 0.076%

    No Known Activations