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

    Neuronpedia

    INDEX
    Explanations

    URLs or web links in the text

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

    web links with ://

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.66
     CURIAM
    -0.61
     poffe
    -0.60
     ſche
    -0.60
     neceff
    -0.59
     pleaſure
    -0.59
     Perſ
    -0.59
     الرياضيه
    -0.57
     poffible
    -0.56
     Houſe
    -0.54
    POSITIVE LOGITS
    ://
    2.30
    :\/\/
    1.20
    ://"
    1.16
    ="//
    0.81
    :///
    0.81
    ://$
    0.68
     للاسماء
    0.59
    __*/
    0.55
    httphttps
    0.54
    :/
    0.51
    Act Density 0.018%

    No Known Activations