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

    Neuronpedia

    INDEX
    Explanations

    references to AWS roles and permissions statements

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

    AWS IAM policies and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ta
    -0.33
     Monte
    -0.31
     advance
    -0.31
     retail
    -0.30
     pah
    -0.30
     ge
    -0.29
     chu
    -0.29
     move
    -0.29
     sla
    -0.29
     Second
    -0.29
    POSITIVE LOGITS
    Autoritní
    0.86
     autorytatywna
    0.84
    WithIOException
    0.77
    GEBURTSDATUM
    0.75
    Diweddarwch
    0.75
     kasarigan
    0.75
    MigrationBuilder
    0.74
    parsedMessage
    0.74
    Personendaten
    0.71
    دانشنامهٔ
    0.70
    Act Density 0.125%

    No Known Activations