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

    Neuronpedia

    INDEX
    Explanations

    town hall meetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vendeurs
    0.60
     Unido
    0.57
     chefs
    0.57
     שי
    0.55
    ibilidade
    0.55
     convenio
    0.55
     registro
    0.54
     restaurantes
    0.54
     empresarios
    0.54
    ፡
    0.54
    POSITIVE LOGITS
    percaya
    0.65
     Earthquake
    0.60
    5
    0.59
    ە
    0.59
    3
    0.57
    peed
    0.57
    <h2>
    0.56
     earthquake
    0.55
    ana
    0.55
    6
    0.54
    Act Density 0.001%

    No Known Activations