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

    Neuronpedia

    INDEX
    Explanations

    Technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     safeg
    -0.07
     Supplementary
    -0.06
     REST
    -0.06
     primaryKey
    -0.06
     recommends
    -0.06
    Showing
    -0.06
     приобрет
    -0.06
     Erd
    -0.06
     queryInterface
    -0.06
    _et
    -0.06
    POSITIVE LOGITS
     Iranian
    0.07
    uteur
    0.07
    Nat
    0.07
    leshoot
    0.06
    werk
    0.06
     nada
    0.06
     Talent
    0.06
    asse
    0.06
     once
    0.06
    .Web
    0.06
    Act Density 1.360%

    No Known Activations