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

    Neuronpedia

    INDEX
    Explanations

    references to geographic or demographic origins

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

    Followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    people from places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hbase
    -0.59
    ]")]
    -0.56
    HomeAsUpEnabled
    -0.55
     GenerationType
    -0.50
     Baillargeon
    -0.50
     kasarigan
    -0.49
     someone
    -0.47
    arraycopy
    -0.47
     Sleeps
    -0.46
    éal
    -0.46
    POSITIVE LOGITS
     whom
    0.86
     who
    0.86
     którzy
    0.82
    Datuak
    0.80
     kteří
    0.71
     quienes
    0.69
    Trama
    0.69
     հղումներ
    0.67
     الذين
    0.67
    who
    0.67
    Act Density 0.225%

    No Known Activations