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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting elements related to programming or markup syntax

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

    multilingual or technical content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InSection
    -0.40
     resort
    -0.37
     imagin
    -0.35
    olivia
    -0.35
    Pyx
    -0.34
    RunWith
    -0.34
    Él
    -0.34
     Outs
    -0.34
     Madrid
    -0.33
     «
    -0.33
    POSITIVE LOGITS
     ब्रेकडाउन
    0.59
    0.57
    verwijspagina
    0.53
     Normdatei
    0.53
     دیکھیے
    0.52
    aarrggbb
    0.51
     réessayer
    0.50
     Wiktionnaire
    0.49
    Datuak
    0.47
    SequentialGroup
    0.47
    Act Density 1.873%

    No Known Activations