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

    Neuronpedia

    INDEX
    Explanations

    inquiries that request information or clarification about a specific topic

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

    introducing a topic/question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ()
    -0.42
     setUsername
    -0.39
     déc
    -0.39
     betweenstory
    -0.37
    transQ
    -0.35
     AssemblyCompany
    -0.33
     ")
    -0.33
     canst
    -0.32
    jsii
    -0.31
     ().
    -0.31
    POSITIVE LOGITS
    RTHOOK
    0.62
    antMatchers
    0.55
    WriteTagHelper
    0.54
    再说
    0.52
    afone
    0.51
     Concerning
    0.51
     展望
    0.51
     Consideration
    0.51
    还有
    0.50
     Parry
    0.50
    Act Density 0.007%

    No Known Activations