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

    Neuronpedia

    INDEX
    Explanations

    references to directories or resources in code syntax

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

    res/ or com/ paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.49
    примеча
    -0.48
     Roskov
    -0.46
    vician
    -0.44
     Porém
    -0.44
     enfans
    -0.43
    sbericht
    -0.42
    ownic
    -0.42
    nezeu
    -0.41
    GEBURTSDATUM
    -0.41
    POSITIVE LOGITS
     elit
    0.60
     صفحات
    0.58
    ComponentModel
    0.52
    literals
    0.47
    MessageOf
    0.45
    MockMvc
    0.45
     Chwiliwch
    0.44
    LocalizedString
    0.43
    EFF
    0.42
    celi
    0.42
    Act Density 0.001%

    No Known Activations