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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the need for additional research or investigation

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

    introducing further additions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mazz
    -0.65
    -0.62
     Kast
    -0.57
    erialized
    -0.55
    SIST
    -0.55
    olymp
    -0.54
     Stodd
    -0.54
    Билгалдахарш
    -0.54
     pageContext
    -0.54
    ilosop
    -0.53
    POSITIVE LOGITS
    Further
    1.37
     Further
    1.34
     FURTHER
    0.93
    further
    0.91
    FURTHER
    0.88
     further
    0.82
    Weiter
    0.60
     Weiter
    0.60
    进一步
    0.60
    urther
    0.57
    Act Density 0.021%

    No Known Activations