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

    Neuronpedia

    INDEX
    Explanations

    words related to requests and confirmations in various contexts

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

    foreign language components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    URLException
    -0.56
    InjectAttribute
    -0.56
    migrationBuilder
    -0.53
    いきましょう
    -0.51
    みましょう
    -0.50
     endforeach
    -0.50
     CommonModule
    -0.50
    textAppearance
    -0.50
    ılmıştır
    -0.49
    RetentionPolicy
    -0.48
    POSITIVE LOGITS
     쓰
    0.73
    쓰
    0.62
     bañ
    0.59
    határoz
    0.56
     dök
    0.56
    foglal
    0.54
     taşı
    0.54
     enfri
    0.54
     Wasch
    0.52
     kaldır
    0.51
    Act Density 0.129%

    No Known Activations