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

    Neuronpedia

    INDEX
    Explanations

    positive evaluations of experiences

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

    Punctuation marks in text

    np_acts-logits-general · gemini-2.0-flash

    end of sentence descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.68
     AssemblyCompany
    -0.61
     AppCompatTheme
    -0.58
    ษัท
    -0.57
     चीज़ों
    -0.56
     isSelected
    -0.55
    Collectors
    -0.55
    
    -0.54
    crites
    -0.53
    urende
    -0.53
    POSITIVE LOGITS
     staff
    0.90
     Staff
    0.76
    staff
    0.73
    Staff
    0.73
     personale
    0.65
    Friendly
    0.64
    :✨
    0.64
    Helpful
    0.63
     Friendly
    0.62
    Everything
    0.62
    Act Density 0.043%

    No Known Activations