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

    Neuronpedia

    INDEX
    Explanations

    specific names and phrases related to legal or technical terms

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

    Garland names and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſche
    -0.62
     EClass
    -0.62
    HomeAsUpEnabled
    -0.60
     ModelRenderer
    -0.59
    MethodManager
    -0.59
     queſta
    -0.59
     ſta
    -0.59
     препратки
    -0.57
    -------
    -0.57
    featureID
    -0.56
    POSITIVE LOGITS
     Garland
    0.95
     Arjun
    0.62
     garland
    0.47
    glie
    0.42
     Soros
    0.41
     Eier
    0.40
     OMITBAD
    0.40
    okhttp
    0.34
    lequin
    0.34
    com
    0.32
    Act Density 0.011%

    No Known Activations