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

    Neuronpedia

    INDEX
    Explanations

    assertions of factuality or confirmation of statements

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

    stating the true nature of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.72
    complexContent
    -0.66
    setDo
    -0.59
     BorderSide
    -0.55
    recated
    -0.53
    fjspx
    -0.53
     AssemblyCompany
    -0.51
     nephe
    -0.50
     fondue
    -0.50
     Coimbatore
    -0.49
    POSITIVE LOGITS
     actually
    1.41
    actually
    1.38
     ACTUALLY
    1.16
     Actually
    1.13
    Actually
    1.10
    really
    0.93
     really
    0.91
     REALLY
    0.83
     realmente
    0.81
     tatsächlich
    0.79
    Act Density 0.017%

    No Known Activations