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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "Der" in various contexts

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

    start with Der

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.77
     itſelf
    -0.74
     uſed
    -0.71
     myſelf
    -0.71
    出版年
    -0.66
    AndEndTag
    -0.66
     purpoſe
    -0.66
     चीज़ों
    -0.65
     raiſ
    -0.65
    googleapis
    -0.65
    POSITIVE LOGITS
     Der
    1.98
    Der
    1.76
     der
    1.52
     DER
    1.41
    der
    1.13
    DER
    1.00
     Derry
    0.82
     Derbyshire
    0.82
     Дер
    0.80
     derives
    0.79
    Act Density 0.004%

    No Known Activations