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

    Neuronpedia

    INDEX
    Explanations

    the presence of conjunctions and relational phrases

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

    between X and Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.75
     FontWeight
    -0.74
    expandindo
    -0.72
     EconPapers
    -0.70
     ProgressDialog
    -0.70
    UIControlState
    -0.69
     BBS
    -0.69
    WireFormatLite
    -0.68
    󠁣
    -0.67
     GenerationType
    -0.66
    POSITIVE LOGITS
     nôtre
    0.35
     siitä
    0.33
     dôle
    0.31
     its
    0.30
     siihen
    0.29
     mahdol
    0.28
     beira
    0.28
     esimer
    0.28
     seura
    0.28
     sekä
    0.27
    Act Density 0.076%

    No Known Activations