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

    Neuronpedia

    INDEX
    Explanations

    the contracted forms of "to be" and "to have"

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

    it's not working

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.70
    ValueStyle
    -0.64
    ainville
    -0.61
    tagHelperRunner
    -0.56
     للمعارف
    -0.56
    AutoField
    -0.54
    艋
    -0.54
    蚪
    -0.53
     StringTokenizer
    -0.52
    تقاوى
    -0.51
    POSITIVE LOGITS
     Villanueva
    0.38
    তথ্যসূত্র
    0.38
     im
    0.38
    stdbool
    0.38
     Sánchez
    0.38
     behavioural
    0.36
    dotta
    0.35
     correspondents
    0.35
     Esposito
    0.35
    RUnlock
    0.35
    Act Density 0.093%

    No Known Activations