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

    Neuronpedia

    INDEX
    Explanations

    statements about equality and capability, particularly in the context of women and families

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

    Comparison or equivalence

    np_acts-logits-general · gemini-2.0-flash

    comparing performance and equality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    หน่อย
    -0.52
     telle
    -0.46
    IsContent
    -0.45
    DebuggerNonUser
    -0.44
    iej
    -0.43
    исленность
    -0.43
    ellem
    -0.43
     cis
    -0.43
    Varios
    -0.43
     Etc
    -0.42
    POSITIVE LOGITS
     equally
    2.27
     Equally
    1.89
     genauso
    1.74
     altrett
    1.59
     igualmente
    1.53
     ebenso
    1.43
     stejně
    1.31
     igual
    1.31
     lika
    1.26
    equ
    1.23
    Act Density 0.469%

    No Known Activations