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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to safety, particularly in relation to preventing damage and contamination

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

    Preventing damage or contamination

    np_acts-logits-general · gemini-2.0-flash

    preventing undesirable outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?
    -0.62
    SharedDtor
    -0.62
    zzleHttp
    -0.62
    ]--;
    -0.61
     PyLong
    -0.58
    TagMode
    -0.57
    setminus
    -0.57
    writeFieldEnd
    -0.55
    __":
    -0.55
    AsUp
    -0.54
    POSITIVE LOGITS
     évent
    0.78
     nantinya
    0.76
     quelconque
    0.67
     dikem
    0.66
     potential
    0.65
    TargetException
    0.65
     futuros
    0.65
     احتم
    0.64
     any
    0.64
     rischio
    0.63
    Act Density 0.584%

    No Known Activations