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

    Neuronpedia

    INDEX
    Explanations

    components related to stealth and blending in with the environment

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

    stealth and invisibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.54
     SafeMath
    -0.52
    LLocation
    -0.47
    AccessorTable
    -0.45
    ChildScrollView
    -0.44
     <<<<<<<<<<<<<<
    -0.44
    enumi
    -0.43
    findpost
    -0.42
    nezeu
    -0.41
     esternos
    -0.41
    POSITIVE LOGITS
     stealth
    0.53
    stealth
    0.52
    visibility
    0.52
     Hide
    0.51
    hide
    0.50
     concealment
    0.48
    invisible
    0.48
     Stealth
    0.48
    Stealth
    0.47
     Visibility
    0.46
    Act Density 0.153%

    No Known Activations