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

    Neuronpedia

    INDEX
    Explanations

    elements related to safety and protective measures in various contexts

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

    stanchion holder rooftop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FormTagHelper
    -0.63
     intptr
    -0.49
    +:+
    -0.46
     TAMBÉM
    -0.46
     Administrativna
    -0.46
    UnitTesting
    -0.45
     lenker
    -0.45
     AssemblyTitle
    -0.45
     zelve
    -0.44
    LookAnd
    -0.43
    POSITIVE LOGITS
     Wikimedijinoj
    0.44
     Component
    0.41
    panels
    0.40
    줍
    0.39
    รรม
    0.39
    ุ่น
    0.38
    commitment
    0.38
     Kom
    0.38
    components
    0.36
    Panel
    0.36
    Act Density 0.099%

    No Known Activations