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

    Neuronpedia

    INDEX
    Explanations

    crucial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Park
    0.47
     légère
    0.46
    mild
    0.42
     тихо
    0.42
    عرض
    0.41
     வந்தால்
    0.41
    抵抗
    0.41
    良好
    0.40
    менты
    0.40
    direct
    0.39
    POSITIVE LOGITS
    🫠
    0.54
    🫣
    0.50
     outpouring
    0.44
    🥹
    0.43
    🫤
    0.43
     unattainable
    0.43
     Kippur
    0.42
    🫶
    0.42
     SwiftUI
    0.41
     uninsured
    0.41
    Act Density 0.001%

    No Known Activations