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

    Neuronpedia

    INDEX
    Explanations

    references to academic authors and citation formats

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

    citation markers like [@

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.81
     autorytatywna
    -0.78
    IUrlHelper
    -0.77
     pleaſure
    -0.77
     المعيارى
    -0.75
     resourceCulture
    -0.73
     ſche
    -0.73
     للاسماء
    -0.73
    :✨
    -0.71
     snippetHide
    -0.68
    POSITIVE LOGITS
     Wirken
    0.43
     study
    0.40
    .
    0.38
     cited
    0.37
     authors
    0.36
     researchers
    0.33
    enangan
    0.33
     notícia
    0.33
    study
    0.32
     They
    0.32
    Act Density 0.068%

    No Known Activations