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

    Neuronpedia

    INDEX
    Explanations

    specific articles and determiners in a text

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

    "la" in different languages

    np_acts-logits-general · gemini-2.0-flash

    la followed by noun/adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.91
     and
    -0.82
    .
    -0.77
    ;
    -0.72
    !
    -0.63
    ?
    -0.61
    —
    -0.59
     solchen
    -0.56
    *
    -0.56
    --
    -0.56
    POSITIVE LOGITS
     latter
    1.01
     whole
    0.87
     slightest
    0.86
     same
    0.84
     HasFactory
    0.80
     aforementioned
    0.76
     moindre
    0.76
     entirety
    0.75
    saurus
    0.75
    ophyll
    0.75
    Act Density 0.021%

    No Known Activations