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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nadal
    -0.09
     xid
    -0.09
    achat
    -0.09
     Gibbs
    -0.08
     katastro
    -0.08
     horoscope
    -0.08
     Gradient
    -0.08
     suicidal
    -0.08
     narciss
    -0.08
     بنسبة
    -0.08
    POSITIVE LOGITS
    .Package
    0.09
    .basename
    0.08
    materiaal
    0.08
    .abspath
    0.08
     liabilities
    0.08
     യു�
    0.08
     LLP
    0.08
    Assets
    0.08
    deps
    0.08
     declares
    0.08
    Act Density 0.005%

    No Known Activations