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

    Neuronpedia

    INDEX
    Explanations

    carb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plans
    -0.72
     Plan
    -0.60
     Cox
    -0.59
     plan
    -0.56
    Plans
    -0.56
     PLANS
    -0.55
     Burns
    -0.53
     plans
    -0.51
     Carb
    -0.47
     us
    -0.47
    POSITIVE LOGITS
    Personensuche
    0.98
     autorytatywna
    0.94
    IsContent
    0.90
    клопе
    0.88
     otomatig
    0.82
     Roskov
    0.81
    Tracce
    0.81
    PreferredItem
    0.79
     незавершена
    0.79
     pinulongan
    0.78
    Act Density 0.139%

    No Known Activations