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

    Neuronpedia

    INDEX
    Explanations

    constructs related to defense mechanisms or protective strategies

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

    Terms related to guarding or shielding

    np_acts-logits-general · gemini-2.0-flash

    protection and defense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.68
    ⓧ
    -0.63
    moveToFirst
    -0.58
     sonde
    -0.53
    usermodel
    -0.53
     händer
    -0.53
    NameInMap
    -0.50
    CodedInputStream
    -0.49
     probing
    -0.48
     discovery
    -0.48
    POSITIVE LOGITS
     protection
    1.84
     protective
    1.65
     protecting
    1.62
     Protection
    1.58
    protection
    1.54
    Protection
    1.53
     protect
    1.50
     protects
    1.47
     Protective
    1.41
     Protecting
    1.40
    Act Density 0.892%

    No Known Activations