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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions and emotional reactions

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

    Text before a contrastive conjunction

    np_acts-logits-general · gemini-2.0-flash

    personal preference contrasting statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abgerufen
    -0.46
     commission
    -0.46
    gesch
    -0.44
    unz
    -0.44
    共有
    -0.43
     effective
    -0.43
     effectively
    -0.41
     commissions
    -0.41
     Commission
    -0.41
     نا
    -0.40
    POSITIVE LOGITS
    MigrationBuilder
    0.90
     seeing
    0.84
     Liked
    0.84
     disambiguazione
    0.84
    Surprised
    0.84
     Feels
    0.82
    Parcelize
    0.81
     ngl
    0.79
     LOVED
    0.79
    Liked
    0.79
    Act Density 0.290%

    No Known Activations