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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SharedPtr
    -0.07
     veterans
    -0.07
     mobility
    -0.07
     عرب
    -0.06
    stitial
    -0.06
    setTitle
    -0.06
     ks
    -0.06
     Thursday
    -0.06
     Login
    -0.06
     --------
    -0.06
    POSITIVE LOGITS
     interrogation
    0.07
     Серед
    0.07
     перевір
    0.07
     voluntarily
    0.06
    omens
    0.06
    .AddSingleton
    0.06
    \Middleware
    0.06
     cripp
    0.06
     cancellationToken
    0.06
     getUrl
    0.06
    Act Density 0.019%

    No Known Activations