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

    Neuronpedia

    INDEX
    Explanations

    compartments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _va
    -0.07
    _on
    -0.07
    fs
    -0.07
    än
    -0.06
    _ll
    -0.06
    ρων
    -0.06
    uentes
    -0.06
    ()
↵
↵
↵
    -0.06
    (),'
    -0.06
    Register
    -0.06
    POSITIVE LOGITS
     человечес
    0.08
     onemoc
    0.07
     subtract
    0.07
     продукції
    0.07
    сько
    0.06
     NBC
    0.06
     Stripe
    0.06
     Letter
    0.06
    Authorized
    0.06
     sab
    0.06
    Act Density 0.023%

    No Known Activations