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

    Neuronpedia

    INDEX
    Explanations

    verbs related to understanding and analysis of evidence or opinions

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

    drawing conclusions and explaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.70
    mpagne
    -0.56
    ाहरण
    -0.55
     AssemblyTitle
    -0.54
    HtmlAttribute
    -0.54
    featureID
    -0.52
    gout
    -0.52
    IntoConstraints
    -0.52
     Colchester
    -0.49
     Theſe
    -0.49
    POSITIVE LOGITS
    SharedDtor
    0.42
    WriteTagHelper
    0.36
     surla
    0.34
    ⓧ
    0.32
    SequentialGroup
    0.30
    ":{"
    0.30
     skriv
    0.29
     arquitectura
    0.29
    werben
    0.29
    Попис
    0.29
    Act Density 0.651%

    No Known Activations