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

    Neuronpedia

    INDEX
    Explanations

    titles and authors in documents

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

    author and title labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.49
    Vidite
    -0.48
    AppRoutingModule
    -0.46
     estadounid
    -0.45
     démocr
    -0.43
    StylePriority
    -0.43
    GraphicsUnit
    -0.42
     Paesi
    -0.42
     arrière
    -0.42
    FormState
    -0.42
    POSITIVE LOGITS
    :✨
    0.57
    NameInMap
    0.52
    \{\\
    0.52
    UrlResolution
    0.50
    EndContext
    0.43
     ModelRenderer
    0.41
    hund
    0.40
    multirow
    0.39
    期刊论文
    0.38
     AssemblyCompany
    0.38
    Act Density 0.000%

    No Known Activations