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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating leadership and capability, particularly in the context of women's empowerment

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

    after verbs (is, has, do, takes)

    np_acts-logits-general · gemini-2.0-flash

    EXISTS AS, simply takes, not correct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.50
    enumi
    -0.46
    oree
    -0.43
     bemerkt
    -0.42
     remarks
    -0.42
     bemer
    -0.40
     antics
    -0.40
     enjoyable
    -0.39
     amusing
    -0.39
     regards
    -0.38
    POSITIVE LOGITS
    تقاوى
    0.54
    expandindo
    0.51
    GIVEREF
    0.46
     Thebes
    0.46
    everywhere
    0.45
    MouseAdapter
    0.44
     AssemblyTitle
    0.43
     communiquez
    0.43
    étoit
    0.42
    fucking
    0.42
    Act Density 0.458%

    No Known Activations