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

    Neuronpedia

    INDEX
    Explanations

    т

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     several
    -0.08
     Os
    -0.07
     Gon
    -0.07
     upset
    -0.07
     ausge
    -0.07
     >=
    -0.07
     pem
    -0.07
    лся
    -0.07
     his
    -0.07
    "These
    -0.07
    POSITIVE LOGITS
    technology
    0.08
    Companies
    0.08
    orelease
    0.08
     movers
    0.08
    📦
    0.08
    收入
    0.07
    fuel
    0.07
    pageTitle
    0.07
    ॱ
    0.07
    _color
    0.07
    Act Density 0.011%

    No Known Activations