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

    Neuronpedia

    INDEX
    Explanations

    references to the word "we"

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

    Followed by "e", "i", "a" or "brt" prefixed words

    np_acts-logits-general · gemini-2.0-flash

    words starting with we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.73
    aarrggbb
    -0.67
    rungsseite
    -0.65
    مصادر
    -0.58
    addLast
    -0.57
     समीक्षाओं
    -0.57
    ímite
    -0.55
     Lohan
    -0.55
     Brethren
    -0.54
     Amis
    -0.52
    POSITIVE LOGITS
     me
    0.57
     Wikimedijinoj
    0.52
     policiales
    0.52
    )$}
    0.51
    writeField
    0.51
     juridiques
    0.49
     obligé
    0.49
     anledning
    0.48
     tecnológicos
    0.47
     maksud
    0.47
    Act Density 0.100%

    No Known Activations