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

    Neuronpedia

    INDEX
    Explanations

    concepts related to protection and safety in various contexts

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

    protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.55
     pageContext
    -0.50
    帖最后由
    -0.48
    GTCX
    -0.44
    BindingSource
    -0.44
     الحره
    -0.42
    iastes
    -0.40
     aapt
    -0.40
    脚注の使い方
    -0.40
    swig
    -0.39
    POSITIVE LOGITS
     protection
    1.75
     protect
    1.59
     Protection
    1.58
     protecting
    1.57
     protective
    1.57
    protection
    1.56
    Protection
    1.56
     protección
    1.48
    Protective
    1.46
     PROTECTION
    1.45
    Act Density 0.082%

    No Known Activations