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

    Neuronpedia

    INDEX
    Explanations

    speech acts or quotes

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

    attributions of speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     drain
    -0.40
     drains
    -0.37
    empêcher
    -0.37
     depot
    -0.36
    منابع
    -0.36
     Pab
    -0.36
    DECREF
    -0.35
     fac
    -0.35
     balance
    -0.34
    Portail
    -0.34
    POSITIVE LOGITS
    XmlAccessType
    0.63
    AndEndTag
    0.63
     وتسجيلات
    0.58
    says
    0.56
     sagt
    0.56
     sagte
    0.56
    httphttps
    0.54
    said
    0.54
     Says
    0.54
     say
    0.53
    Act Density 0.029%

    No Known Activations