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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contextual meanings

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    words from different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Signalez
    -0.72
    #+#
    -0.59
     &___
    -0.54
    migrationBuilder
    -0.54
    };*/
    -0.52
    +:+
    -0.50
    ❸
    -0.50
    fordshire
    -0.50
    ″]
    -0.50
    toplankton
    -0.50
    POSITIVE LOGITS
     semuanya
    0.39
     allemaal
    0.38
     otomatig
    0.36
     dignité
    0.36
    desenho
    0.36
     dorados
    0.35
    aspetto
    0.35
     مفص
    0.34
     vlees
    0.34
     reír
    0.33
    Act Density 0.805%

    No Known Activations