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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or structural elements in text, particularly the presence of tags or special characters

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

    Often appears before or after names/initials

    np_acts-logits-general · gemini-2.0-flash

    separators or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     greateſt
    -0.82
     purpoſe
    -0.70
     cauſe
    -0.65
     houſe
    -0.65
     Diſ
    -0.64
     reaſon
    -0.64
     Большая
    -0.62
     diſt
    -0.61
     inſ
    -0.61
     Houſe
    -0.61
    POSITIVE LOGITS
     \&
    0.84
     et
    0.84
     referenties
    0.76
     Jr
    0.68
     &
    0.62
     <=",
    0.62
     coworkers
    0.62
    httphttps
    0.62
     متعلقه
    0.61
     الرياضيه
    0.60
    Act Density 0.207%

    No Known Activations