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

    Neuronpedia

    INDEX
    Explanations

    dialogues and conversational interactions

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

    dialogue fillers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Хьажоргаш
    -0.58
    NameValuePair
    -0.55
    GenerationType
    -0.53
    SerializedName
    -0.51
     defied
    -0.43
    ----</
    -0.43
    graphicx
    -0.41
     pathologies
    -0.41
    Gemeinden
    -0.40
     coales
    -0.39
    POSITIVE LOGITS
    EndInit
    0.60
     anſ
    0.40
     houſe
    0.39
    oredCriteria
    0.39
     snippetHide
    0.38
    BeginInit
    0.38
     ویکی‌پدیا
    0.36
    excuse
    0.36
    abestanden
    0.36
     PROCED
    0.34
    Act Density 0.063%

    No Known Activations