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

    Neuronpedia

    INDEX
    Explanations

    references to identity and anonymity

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

    identity and anonymity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    place
    -0.39
    DIPSETTING
    -0.38
     سما
    -0.38
    ne
    -0.37
     Poor
    -0.37
    ètre
    -0.37
    ẩm
    -0.37
    Poor
    -0.36
     Leber
    -0.36
     Golf
    -0.35
    POSITIVE LOGITS
     مشين
    0.64
    ContentAsync
    0.60
    CloseOperation
    0.58
    IntoConstraints
    0.56
     pinulongan
    0.55
     Chriftian
    0.55
     AssemblyCompany
    0.54
     Normdatei
    0.54
     perſon
    0.52
     identité
    0.52
    Act Density 0.030%

    No Known Activations