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

    Neuronpedia

    INDEX
    Explanations

    specific class names and object identifiers in code

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

    policy, lifecycle, or device configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.98
     незавершена
    -0.98
     otomatig
    -0.88
    IntoConstraints
    -0.87
    ьаж
    -0.85
     snippetHide
    -0.84
    ScopeManager
    -0.82
    MemoryWarning
    -0.80
    featureID
    -0.79
     queſta
    -0.79
    POSITIVE LOGITS
    2
    0.39
    TM
    0.38
    sk
    0.36
     Ras
    0.36
     Foundation
    0.35
    .
    0.35
     
    0.35
    </h1>
    0.35
    Web
    0.34
     Cabral
    0.34
    Act Density 0.006%

    No Known Activations