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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public disclosures or public statements

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

    publicly followed by action or status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     borboleta
    -0.43
     indispensables
    -0.41
    lccn
    -0.41
    SneakyThrows
    -0.40
     mision
    -0.40
    import
    -0.40
     of
    -0.39
     recomendaciones
    -0.39
     betreff
    -0.39
    Step
    -0.38
    POSITIVE LOGITS
     publicly
    2.09
     openly
    1.34
     öffentlich
    1.17
     privately
    1.00
     pública
    0.98
     loudly
    0.89
     публи
    0.88
    公开
    0.88
     publi
    0.86
    公開
    0.85
    Act Density 0.005%

    No Known Activations