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

    Neuronpedia

    INDEX
    Explanations

    names and their corresponding sentiments in narrative contexts

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

    followed by apostrophes or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    foreign names or words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -1.08
     nakalista
    -0.91
    $")
    -0.79
    AndroidJUnit
    -0.79
    BibitemShut
    -0.74
     مشين
    -0.72
     kasarigan
    -0.72
    ")}
    -0.70
    __":
    -0.70
    )++;
    -0.70
    POSITIVE LOGITS
    ’
    0.68
    '
    0.64
     who
    0.64
     had
    0.62
     and
    0.55
     was
    0.54
     himself
    0.54
     did
    0.53
     knew
    0.53
    ,
    0.53
    Act Density 0.450%

    No Known Activations