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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries related to understanding processes or evaluating situations

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

    how to figure out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.56
    __*/
    -0.44
    ंदीखरीदारी
    -0.42
     Administrativna
    -0.42
    uxxxx
    -0.42
     réessayer
    -0.41
     الرياضيه
    -0.40
    Архівовано
    -0.39
     Мексичка
    -0.39
     autorytatywna
    -0.38
    POSITIVE LOGITS
     figured
    0.71
     figuring
    0.60
     Arrangement
    0.57
     Arrangements
    0.56
     ARRANG
    0.53
    Arrangement
    0.53
    figured
    0.52
     arrangements
    0.52
    kward
    0.52
     descobrir
    0.51
    Act Density 0.019%

    No Known Activations