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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and their statements or actions

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

    Follows specific punctuation or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    Trump tweets and investigations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     courir
    -0.44
    ContentLoaded
    -0.44
     فرهنگی
    -0.43
     fundamentally
    -0.40
     Ebers
    -0.40
     concaten
    -0.39
     fer
    -0.39
     Hike
    -0.39
     Trek
    -0.39
     arguments
    -0.38
    POSITIVE LOGITS
    $_['
    0.83
    +#+#
    0.57
    ########.
    0.53
    новништво
    0.48
    MessageOf
    0.48
     Trump
    0.47
     OMITBAD
    0.45
    Trump
    0.44
    Билгалдахарш
    0.42
    Personendaten
    0.42
    Act Density 0.134%

    No Known Activations