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

    Neuronpedia

    INDEX
    Explanations

    references to specific concepts or instances, particularly in a comparative or relational context

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

    Prepositions in multiple languages

    np_acts-logits-general · gemini-2.0-flash

    German and Russian prepositions and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -0.83
     itſelf
    -0.80
     myſelf
    -0.78
     iſt
    -0.76
     untere
    -0.76
     contextLoads
    -0.76
     pleaſure
    -0.76
     Majefty
    -0.74
     Anſ
    -0.74
     ehemalige
    -0.72
    POSITIVE LOGITS
     einem
    0.79
     dem
    0.69
     unui
    0.65
     unei
    0.64
    于
    0.55
     einer
    0.55
    eriks
    0.55
    於
    0.51
     tej
    0.50
    ůli
    0.50
    Act Density 0.022%

    No Known Activations