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

    Neuronpedia

    INDEX
    Explanations

    comparative terms related to assumptions and their strengths in a theoretical context

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

    comparative strength

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserScript
    -0.46
    SequentialGroup
    -0.44
    -------------</
    -0.42
    #+#
    -0.42
    XmlRootElement
    -0.41
     שוליים
    -0.40
    Dab
    -0.40
    Liz
    -0.38
    $_['
    -0.38
    ValueStyle
    -0.38
    POSITIVE LOGITS
    ChildScrollView
    0.48
    Törté
    0.44
     pincel
    0.43
     RuntimeError
    0.43
    Fordítás
    0.43
     Literatura
    0.41
     Pesquisa
    0.40
     familles
    0.40
    //
    0.40
     logro
    0.40
    Act Density 0.769%

    No Known Activations