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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     desperation
    -0.07
     перел
    -0.07
     plan
    -0.06
    icates
    -0.06
     xb
    -0.06
     knocking
    -0.06
     desp
    -0.06
     estimation
    -0.06
    wendung
    -0.06
     binder
    -0.06
    POSITIVE LOGITS
     Listener
    0.07
     py
    0.06
     声
    0.06
     должен
    0.06
    čů
    0.06
    ABI
    0.06
     CRM
    0.06
    VES
    0.06
     возник
    0.05
     حافظه
    0.05
    Act Density 0.077%

    No Known Activations