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

    Neuronpedia

    INDEX
    Explanations

    terms related to minimizing negative impacts and suffering, particularly in a medical or ethical context

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

    reducing adverse effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    liebte
    -0.40
     установ
    -0.32
    eseorang
    -0.31
     rallado
    -0.31
     constamment
    -0.30
     Ral
    -0.30
     supérieurs
    -0.30
    SequentialGroup
    -0.30
     vzor
    -0.30
     palanca
    -0.30
    POSITIVE LOGITS
     autorytatywna
    0.88
    IndentedString
    0.86
    RUnlock
    0.68
     snippetHide
    0.68
    Билгалдахарш
    0.67
    0.67
     فريبيس
    0.64
    ロウィン
    0.64
     referrerpolicy
    0.63
    StoryboardSegue
    0.63
    Act Density 0.028%

    No Known Activations