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

    Neuronpedia

    INDEX
    Explanations

    references to cardinal numbers and centuries

    oai_token-act-pair · gemini-2.0-flash

    centuries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    حياتها
    -0.72
     <>",
    -0.72
    ⓧ
    -0.71
     للاسماء
    -0.69
    hyrchwyd
    -0.68
    Aholisi
    -0.68
    #+#
    -0.60
    tagHelperRunner
    -0.59
    сылкі
    -0.58
    Хьажоргаш
    -0.57
    POSITIVE LOGITS
     XX
    0.95
     twentieth
    0.94
     XIX
    0.89
     nineteenth
    0.89
     century
    0.85
     eighteenth
    0.84
     XVII
    0.84
     seventeenth
    0.82
     XVIII
    0.82
     sixteenth
    0.81
    Act Density 0.881%

    No Known Activations